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

    Neuronpedia

    INDEX
    Explanations

    target

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Management
    -0.07
     spyOn
    -0.07
    _match
    -0.07
    .getCode
    -0.07
     useCallback
    -0.07
    Gener
    -0.07
     tedious
    -0.07
    toPromise
    -0.07
    mouseout
    -0.07
    쥐
    -0.07
    POSITIVE LOGITS
    lesi
    0.08
    ライ
    0.07
    인이
    0.07
    liga
    0.07
    例
    0.07
    リン
    0.07
    梓
    0.07
    configs
    0.06
    neh
    0.06
    lor
    0.06
    Act Density 0.021%

    No Known Activations