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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ｌ
    -0.06
     heterosexual
    -0.06
     hr
    -0.06
     Oregon
    -0.06
     материал
    -0.06
    Li
    -0.06
    .cur
    -0.06
    밀
    -0.06
     あ
    -0.06
    _study
    -0.06
    POSITIVE LOGITS
    Days
    0.06
    747
    0.06
    _ARCH
    0.06
     Kont
    0.06
    ايي
    0.06
     affected
    0.06
    _SPLIT
    0.06
     Dış
    0.06
    lh
    0.06
    更多
    0.06
    Act Density 0.000%

    No Known Activations