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

    Neuronpedia

    INDEX
    Explanations

    missing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    回应
    -0.07
    沖
    -0.07
    打得
    -0.07
    ClassNotFoundException
    -0.07
    Searching
    -0.06
    (controller
    -0.06
    ↗
    -0.06
    汗水
    -0.06
    走向
    -0.06
    忽
    -0.06
    POSITIVE LOGITS
     Rh
    0.08
    瑛
    0.07
    زار
    0.07
     Fay
    0.07
     четыре
    0.07
     Opera
    0.07
     Education
    0.07
     Feed
    0.07
    分管
    0.06
     Forms
    0.06
    Act Density 0.006%

    No Known Activations