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

    Neuronpedia

    INDEX
    Explanations

    Apache

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isor
    -0.07
    来自
    -0.06
     Dam
    -0.06
    末
    -0.06
     [&](
    -0.06
    ueur
    -0.06
     外部
    -0.06
    Or
    -0.06
     Pul
    -0.06
    _RULE
    -0.06
    POSITIVE LOGITS
     merkez
    0.07
    clientId
    0.07
    encoding
    0.07
    喜
    0.07
    .header
    0.06
     loud
    0.06
     Wid
    0.06
    apixel
    0.06
     değiştir
    0.06
     sağ
    0.06
    Act Density 0.003%

    No Known Activations