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

    Neuronpedia

    INDEX
    Explanations

    adjectives of importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tarafından
    -0.07
    _EXPR
    -0.07
     shredded
    -0.07
     Westminster
    -0.07
     identification
    -0.06
    errals
    -0.06
    (R
    -0.06
     پرداخت
    -0.06
     visto
    -0.06
     waterfall
    -0.06
    POSITIVE LOGITS
    忠
    0.07
     corrupt
    0.06
     даль
    0.06
    "struct
    0.06
    extView
    0.06
    /The
    0.06
     nhanh
    0.06
    ulsive
    0.06
     the
    0.06
     dependent
    0.06
    Act Density 0.060%

    No Known Activations