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

    Neuronpedia

    INDEX
    Explanations

    Forwarding/passing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    avatars
    -0.07
     atheist
    -0.07
    �
    -0.07
    茄子
    -0.07
    ༒
    -0.06
     Easter
    -0.06
    izzes
    -0.06
     killed
    -0.06
     onMouse
    -0.06
     athe
    -0.06
    POSITIVE LOGITS
     ההת
    0.07
     تقديم
    0.07
    *num
    0.07
     למע
    0.07
    _end
    0.06
     gunman
    0.06
    实事求是
    0.06
     בהת
    0.06
    转换
    0.06
    соедин
    0.06
    Act Density 0.056%

    No Known Activations