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
    تد
    -0.07
    (levels
    -0.06
    Lady
    -0.06
    ifier
    -0.06
    esome
    -0.06
     egret
    -0.06
     Algebra
    -0.06
    dia
    -0.06
     standby
    -0.06
    itemap
    -0.06
    POSITIVE LOGITS
     thous
    0.07
     hers
    0.06
     architecture
    0.06
     repositories
    0.06
    ीं।
    0.06
    .wordpress
    0.06
    日本
    0.06
     unearth
    0.06
     moderation
    0.06
     району
    0.06
    Act Density 0.015%

    No Known Activations