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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal reflections and inquiries

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

    trust and email updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.52
    AttributeSet
    -0.40
     становника
    -0.40
     дописавши
    -0.39
     resourceCulture
    -0.39
    QMetaType
    -0.38
    inigte
    -0.37
    ᅠ
    -0.37
     âmes
    -0.37
    orithm
    -0.37
    POSITIVE LOGITS
    Trust
    0.50
    Datuak
    0.47
     trust
    0.45
     Trust
    0.45
    PMailer
    0.44
    trust
    0.42
     مرئيه
    0.40
    contentLoaded
    0.39
     تانيه
    0.39
     arrive
    0.38
    Act Density 0.055%

    No Known Activations