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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and their contexts

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

    location followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.56
    rungsseite
    -0.56
    DoubleQuotes
    -0.52
     nonUne
    -0.52
    IntoConstraints
    -0.52
    -0.50
    WebVitals
    -0.50
     régal
    -0.49
    PerformLayout
    -0.48
     vœ
    -0.48
    POSITIVE LOGITS
    ScopeManager
    0.41
     knocked
    0.38
     mergeFrom
    0.36
    Scénario
    0.35
     مشين
    0.33
    FilterChain
    0.33
     schlaf
    0.32
     half
    0.32
     chó
    0.30
     fost
    0.30
    Act Density 0.026%

    No Known Activations