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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שיל
    -0.07
     CEL
    -0.07
    .setTag
    -0.07
     protects
    -0.07
    مقال
    -0.06
    ߩ
    -0.06
    .JMenuItem
    -0.06
    ὃ
    -0.06
    绢
    -0.06
    츕
    -0.06
    POSITIVE LOGITS
    老婆
    0.07
    当天
    0.07
     operators
    0.07
     Springs
    0.07
    脚步
    0.07
    潮流
    0.07
     Webb
    0.07
    恋爱
    0.06
     Mog
    0.06
    liament
    0.06
    Act Density 0.007%

    No Known Activations