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

    Neuronpedia

    INDEX
    Explanations

    Consortium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    189
    -0.07
     Combined
    -0.07
     Abbott
    -0.07
    Bot
    -0.07
    movies
    -0.06
     か
    -0.06
     administered
    -0.06
    zą
    -0.06
    .header
    -0.06
     два
    -0.06
    POSITIVE LOGITS
    .espresso
    0.06
    ��
    0.06
    _ABI
    0.06
    셀
    0.06
     जबक
    0.06
    amide
    0.06
    만
    0.06
    議
    0.06
     fallback
    0.06
    ासन
    0.05
    Act Density 0.000%

    No Known Activations