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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ild
    -0.07
     люди
    -0.07
     Reid
    -0.07
     Ils
    -0.07
    řet
    -0.07
    بود
    -0.06
     submission
    -0.06
    REN
    -0.06
    .builders
    -0.06
     marches
    -0.06
    POSITIVE LOGITS
    _softc
    0.06
    `.`
    0.06
     onCancelled
    0.06
     Apost
    0.06
    OnError
    0.06
    вести
    0.06
     acknowled
    0.06
    renal
    0.06
    _PROF
    0.06
     세상
    0.06
    Act Density 0.003%

    No Known Activations