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

    Neuronpedia

    INDEX
    Explanations

    Further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fo
    -0.07
    -out
    -0.07
     torch
    -0.07
    譬
    -0.07
     Fast
    -0.07
    _unref
    -0.07
     We
    -0.07
     CP
    -0.07
    +E
    -0.06
    ﺊ
    -0.06
    POSITIVE LOGITS
    :',↵
    0.07
     france
    0.07
     WATCH
    0.06
    家族
    0.06
    你的
    0.06
    .
↵
    0.06
    Charlotte
    0.06
    ثار
    0.06
     dean
    0.06
    ussia
    0.06
    Act Density 0.004%

    No Known Activations