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
    .errors
    -0.06
     H
    -0.06
     geopolitical
    -0.06
     enlight
    -0.06
     peux
    -0.06
    їх
    -0.06
     Kash
    -0.06
    derived
    -0.06
     undeniable
    -0.06
    .Ch
    -0.06
    POSITIVE LOGITS
     Symbols
    0.07
     çeşit
    0.07
    �
    0.06
     breve
    0.06
    ěle
    0.06
    svm
    0.06
     شکست
    0.06
    uç
    0.06
    OMUX
    0.06
    _speed
    0.06
    Act Density 0.000%

    No Known Activations