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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    企
    -0.07
     Imported
    -0.07
     epsilon
    -0.07
    cff
    -0.07
    Encoded
    -0.07
    secured
    -0.07
     huge
    -0.07
     shaved
    -0.07
     Healthcare
    -0.07
    _large
    -0.07
    POSITIVE LOGITS
    或其他
    0.07
    ㄛ
    0.07
    aci
    0.07
    //#
    0.06
    款式
    0.06
    Christopher
    0.06
    績
    0.06
    一般的
    0.06
    OFF
    0.06
    쓸
    0.06
    Act Density 0.001%

    No Known Activations