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

    Neuronpedia

    INDEX
    Explanations

    Clamping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPA
    -0.08
    商业模式
    -0.07
    /channel
    -0.07
     StreamReader
    -0.07
     simp
    -0.07
    hashCode
    -0.07
    逍遥
    -0.07
     Ages
    -0.07
     değil
    -0.06
    .STATE
    -0.06
    POSITIVE LOGITS
    %'
    0.08
    練
    0.07
    %"),↵
    0.07
     לק
    0.06
    㭎
    0.06
    strlen
    0.06
     yaşadığı
    0.06
    obsług
    0.06
     Sony
    0.06
    崿
    0.06
    Act Density 0.006%

    No Known Activations