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

    Neuronpedia

    INDEX
    Explanations

    code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     μόνο
    -0.07
     セ
    -0.06
    ژن
    -0.06
     sexuality
    -0.06
    очь
    -0.06
     devastating
    -0.06
    :{}
    -0.06
     serve
    -0.05
    خت
    -0.05
     ------------------------------------------------
    -0.05
    POSITIVE LOGITS
     Tom
    0.07
    0.07
    /releases
    0.07
    iyat
    0.07
     boxShadow
    0.06
     specify
    0.06
    -fr
    0.06
    iano
    0.06
    NTAX
    0.06
    0.06
    Act Density 0.003%

    No Known Activations