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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    冷漠
    -0.07
    .VERTICAL
    -0.07
    🌂
    -0.07
    Ḻ
    -0.07
    _bulk
    -0.07
    ߗ
    -0.07
     pareja
    -0.06
     хозя
    -0.06
    WORK
    -0.06
    НЫ
    -0.06
    POSITIVE LOGITS
     Ou
    0.08
    读后
    0.08
    (after
    0.07
    <<<
    0.07
    重回
    0.07
    pth
    0.07
     중
    0.07
     trough
    0.07
     om
    0.07
    车间
    0.07
    Act Density 0.026%

    No Known Activations