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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پل
    -0.07
    iyas
    -0.07
    로는
    -0.07
    館
    -0.06
    ularity
    -0.06
    516
    -0.06
    ken
    -0.06
     прит
    -0.06
    _need
    -0.06
    <data
    -0.06
    POSITIVE LOGITS
     msgid
    0.06
     sidelines
    0.06
    .MenuStrip
    0.06
     Ankara
    0.06
    �
    0.06
    Edge
    0.06
    ienen
    0.06
    技能
    0.06
     provoc
    0.06
    cerr
    0.06
    Act Density 0.064%

    No Known Activations