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
    asured
    -0.08
    🐆
    -0.07
    aze
    -0.07
    滋
    -0.07
    涤
    -0.07
    モ
    -0.07
    (uuid
    -0.06
    ꪻ
    -0.06
    纹
    -0.06
    Davis
    -0.06
    POSITIVE LOGITS
    _flat
    0.08
     fondo
    0.07
     الدكت
    0.07
     chat
    0.07
     apartheid
    0.07
    _player
    0.07
     بال
    0.07
    'util
    0.06
     rb
    0.06
    .smart
    0.06
    Act Density 0.002%

    No Known Activations