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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yönetic
    -0.07
    |/
    -0.07
    Josh
    -0.06
     Welfare
    -0.06
    Karen
    -0.06
    .,↵
    -0.06
    $view
    -0.06
    Visitor
    -0.06
    ---↵↵
    -0.06
     Timothy
    -0.06
    POSITIVE LOGITS
     yaptık
    0.07
    .Token
    0.07
    toFixed
    0.06
    升
    0.06
    -alpha
    0.06
    目标
    0.06
    _regularizer
    0.06
     अल
    0.06
    _con
    0.06
     concentrating
    0.06
    Act Density 0.002%

    No Known Activations