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

    Neuronpedia

    INDEX
    Explanations

    say "->"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不见了
    -0.08
    -Bold
    -0.07
    edes
    -0.07
    筇
    -0.07
    نبي
    -0.07
    zion
    -0.07
    unde
    -0.07
     NDEBUG
    -0.07
     בעצם
    -0.07
    ickt
    -0.07
    POSITIVE LOGITS
     Org
    0.07
    复杂的
    0.07
    FS
    0.06
    钎
    0.06
    _raise
    0.06
     assists
    0.06
    Ƥ
    0.06
    _patterns
    0.06
     ответ
    0.06
    民政局
    0.06
    Act Density 0.022%

    No Known Activations