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

    Neuronpedia

    INDEX
    Explanations

    agon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sor
    -0.07
     silent
    -0.07
     chứ
    -0.07
     toll
    -0.07
     ante
    -0.06
     mys
    -0.06
    硬化
    -0.06
    .feature
    -0.06
     peanut
    -0.06
     halt
    -0.06
    POSITIVE LOGITS
    arians
    0.07
    ocities
    0.07
     Arithmetic
    0.07
     Garc
    0.07
    哲
    0.07
    博士学位
    0.07
    锋
    0.07
    国防
    0.07
     Opening
    0.07
    _docs
    0.06
    Act Density 0.001%

    No Known Activations