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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зна
    -0.06
    -0.06
     Rossi
    -0.06
    JECTED
    -0.06
    르
    -0.06
    тив
    -0.06
    وسی
    -0.06
     sle
    -0.06
    сяг
    -0.06
    Evaluate
    -0.06
    POSITIVE LOGITS
    ."""
    0.07
    帮助
    0.07
    ,,,
    0.07
    AGR
    0.06
    訂
    0.06
     comentarios
    0.06
    azon
    0.06
    -top
    0.06
     όμως
    0.06
    _PKT
    0.06
    Act Density 0.038%

    No Known Activations