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

    Neuronpedia

    INDEX
    Explanations

    section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}'.
    -0.07
    rede
    -0.07
    ackets
    -0.07
     herself
    -0.07
     Dev
    -0.07
     Rights
    -0.07
    Del
    -0.07
     Ing
    -0.07
     Freedom
    -0.07
    수를
    -0.07
    POSITIVE LOGITS
    324
    0.06
    ＾
    0.06
    表情
    0.06
    ，存于
    0.06
    .dateTime
    0.06
    icemail
    0.06
    灯
    0.06
     모
    0.06
     chlorine
    0.06
     評価
    0.06
    Act Density 0.028%

    No Known Activations