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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ando
    -0.07
    �
    -0.07
    َة
    -0.07
    erox
    -0.07
    spar
    -0.06
    erg
    -0.06
     Qi
    -0.06
     fingerprint
    -0.06
     Hercules
    -0.06
     пор
    -0.06
    POSITIVE LOGITS
     дека
    0.07
    董事
    0.06
    报告
    0.06
     outcry
    0.06
    couz
    0.06
     Donetsk
    0.06
    )("
    0.06
     ovarian
    0.06
    Tại
    0.06
    -runner
    0.05
    Act Density 0.015%

    No Known Activations