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

    Neuronpedia

    INDEX
    Explanations

    elections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    压
    -0.07
    ienen
    -0.07
     개인
    -0.07
    ackson
    -0.06
    𝗺
    -0.06
    ここまで
    -0.06
     ن
    -0.06
    {};↵
    -0.06
     diplomatic
    -0.06
    ɓ
    -0.06
    POSITIVE LOGITS
     wants
    0.07
    want
    0.07
    購
    0.07
     circumstances
    0.07
    ecture
    0.07
    MODEL
    0.07
     <![
    0.07
    出版社
    0.07
     vrouw
    0.07
    0.06
    Act Density 0.051%

    No Known Activations