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

    Neuronpedia

    INDEX
    Explanations

    maintenance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ילים
    -0.08
    _MATH
    -0.07
    oplay
    -0.07
    约会
    -0.07
    -map
    -0.07
     Aur
    -0.07
     donors
    -0.07
     Celebrity
    -0.07
    -Pacific
    -0.07
    \Application
    -0.07
    POSITIVE LOGITS
    Deleted
    0.08
     дем
    0.07
     בחי
    0.07
    嘈
    0.07
    звезд
    0.07
    cached
    0.07
     noisy
    0.07
     кредит
    0.07
     synthesized
    0.07
     viv
    0.07
    Act Density 0.030%

    No Known Activations