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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kommt
    -0.08
    .radio
    -0.07
    Username
    -0.07
     Cond
    -0.07
    失控
    -0.06
    .list
    -0.06
    띠
    -0.06
    hi
    -0.06
    $request
    -0.06
     Outstanding
    -0.06
    POSITIVE LOGITS
    遆
    0.07
    _CONSTANT
    0.07
     WORK
    0.07
    碨
    0.07
    ทธ
    0.07
    ILLISECONDS
    0.07
    嘁
    0.06
    /operators
    0.06
    (vector
    0.06
     activ
    0.06
    Act Density 0.004%

    No Known Activations