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

    Neuronpedia

    INDEX
    Explanations

    words related to legal actions or consequences

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

    Punctuation followed by reporting verbs

    np_acts-logits-general · gemini-2.0-flash

    reporting attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لينك
    -0.63
    )++;
    -0.57
     Infatti
    -0.48
     gradova
    -0.48
    arParams
    -0.48
    QSize
    -0.48
    ControllerAdvice
    -0.48
    PathParam
    -0.46
    anei
    -0.45
    CPtr
    -0.45
    POSITIVE LOGITS
     reports
    1.10
     Reports
    0.95
    reports
    0.93
     reported
    0.92
    Reports
    0.89
     REPORTS
    0.89
     Reported
    0.83
    reported
    0.82
     передает
    0.81
     according
    0.81
    Act Density 0.145%

    No Known Activations