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

    Neuronpedia

    INDEX
    Explanations

    .__

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     injury
    -0.07
    ズ
    -0.07
     Hole
    -0.07
    ورا
    -0.06
     vans
    -0.06
    _ROWS
    -0.06
    _DOC
    -0.06
    c
    -0.06
     inquiry
    -0.06
    (admin
    -0.06
    POSITIVE LOGITS
    [property
    0.08
     combine
    0.07
     表
    0.07
    adjust
    0.06
    fuscated
    0.06
    omik
    0.06
     dép
    0.06
     SCIP
    0.06
    Combine
    0.06
    .Create
    0.06
    Act Density 0.002%

    No Known Activations