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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("/")
    -0.07
     rou
    -0.07
    湄
    -0.07
     Uph
    -0.07
    _arr
    -0.06
    _m
    -0.06
     Producto
    -0.06
    ㅋ
    -0.06
    엶
    -0.06
    ,top
    -0.06
    POSITIVE LOGITS
    غير
    0.08
    copyright
    0.06
    bearer
    0.06
    ert
    0.06
    .annotation
    0.06
    源
    0.06
    (Default
    0.06
    ython
    0.06
    derived
    0.06
    ception
    0.06
    Act Density 0.024%

    No Known Activations