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

    Neuronpedia

    INDEX
    Explanations

    Writers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentence
    -0.07
     judged
    -0.07
     enviado
    -0.06
    女性
    -0.06
     pay
    -0.06
     surpassed
    -0.06
    [h
    -0.06
    errs
    -0.06
     guarding
    -0.06
     Survey
    -0.06
    POSITIVE LOGITS
    getCell
    0.07
    ุคคล
    0.07
    řet
    0.07
     componentDidUpdate
    0.07
    cken
    0.07
     componentWill
    0.06
    .poi
    0.06
     fend
    0.06
     Guzzle
    0.06
    цо
    0.06
    Act Density 0.022%

    No Known Activations