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

    Neuronpedia

    INDEX
    Explanations

    Math sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Left
    -0.08
    Sa
    -0.07
    ippi
    -0.07
    xiv
    -0.07
    .Play
    -0.07
     Aren
    -0.07
    <Type
    -0.06
    .Int
    -0.06
    _Entry
    -0.06
    inars
    -0.06
    POSITIVE LOGITS
     signaling
    0.07
     obdob
    0.06
     мам
    0.06
     FD
    0.06
     образ
    0.06
     منظور
    0.06
    �
    0.06
     eğitim
    0.06
    安装
    0.06
     张
    0.06
    Act Density 0.009%

    No Known Activations