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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and output statements

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

    scripting command codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.61
     estekak
    -0.60
    Manbalar
    -0.59
    parsedMessage
    -0.58
    styleType
    -0.57
    tagHelperRunner
    -0.57
    Personensuche
    -0.57
     autorytatywna
    -0.56
    省市镇
    -0.56
    хьтан
    -0.56
    POSITIVE LOGITS
     Ground
    0.34
    bow
    0.32
    ňov
    0.31
    initro
    0.31
     dow
    0.31
     ground
    0.31
    pins
    0.30
     Joc
    0.30
    tvguidetime
    0.30
     فري
    0.29
    Act Density 0.048%

    No Known Activations