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

    Neuronpedia

    INDEX
    Explanations

    Technical/Code related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [{"
    -0.09
    販
    -0.07
     单
    -0.06
    Это
    -0.06
    ер
    -0.06
    _greater
    -0.06
    ників
    -0.06
    лиц
    -0.06
    erson
    -0.06
    []}
    -0.06
    POSITIVE LOGITS
     continuation
    0.07
     AssemblyTitle
    0.06
    straints
    0.06
     치
    0.06
     horrifying
    0.06
    ै.
    0.06
    verage
    0.06
     dislike
    0.06
     longstanding
    0.06
    合作
    0.06
    Act Density 0.000%

    No Known Activations