Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and expressions of enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    foreign language and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that introduce or express an evaluative/opinionative stance (judgments, endorsements, or assessments).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.60
     consensus
    -0.45
     Consensus
    -0.43
    TargetException
    -0.40
     Campionato
    -0.38
     context
    -0.37
     ब्रेकडाउन
    -0.35
     devices
    -0.34
    aktur
    -0.34
     trump
    -0.33
    POSITIVE LOGITS
    UnusedPrivate
    0.58
    WebVitals
    0.58
     înc
    0.55
    MLLoader
    0.52
    +:+
    0.49
     Majefty
    0.49
    berdayakan
    0.48
    offsetof
    0.47
     vänner
    0.46
    JspWriter
    0.46
    Act Density 0.000%

    No Known Activations