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

    Neuronpedia

    INDEX
    Explanations

    Code, errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Cs
    -0.07
    GMEM
    -0.06
     swollen
    -0.06
    .threshold
    -0.06
     sectional
    -0.06
     BCE
    -0.06
     Ful
    -0.06
     bullish
    -0.05
    ニー
    -0.05
     možnosti
    -0.05
    POSITIVE LOGITS
     Entrepreneur
    0.07
    prene
    0.06
     thứ
    0.06
    념
    0.06
    ايا
    0.06
    arine
    0.06
    	fire
    0.06
     firing
    0.06
     snel
    0.06
     궁
    0.06
    Act Density 0.012%

    No Known Activations