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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    حلة
    -0.07
     scrambling
    -0.07
     школь
    -0.07
    手脚
    -0.07
    ﲠ
    -0.07
    樨
    -0.07
    科学研究
    -0.07
    ugin
    -0.07
     Quint
    -0.06
    :],
    -0.06
    POSITIVE LOGITS
    /post
    0.08
     канал
    0.07
    .Enabled
    0.07
    -U
    0.07
     Binary
    0.07
    承诺
    0.07
     üyeler
    0.07
    /package
    0.07
    ー
    0.06
    昭
    0.06
    Act Density 0.040%

    No Known Activations