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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gem
    -0.07
     balance
    -0.07
     coins
    -0.07
     equation
    -0.06
    躬
    -0.06
     storia
    -0.06
    化学
    -0.06
    (command
    -0.06
     وزارة
    -0.06
    外汇
    -0.06
    POSITIVE LOGITS
     kỳ
    0.07
     feminists
    0.07
    _SECTION
    0.07
    نب
    0.07
    ㏃
    0.06
     trúc
    0.06
    Ἄ
    0.06
    _addr
    0.06
    ­ing
    0.06
     NF
    0.06
    Act Density 0.007%

    No Known Activations