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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peru
    -0.08
     Комп
    -0.08
     Друг
    -0.07
    .topic
    -0.07
     topic
    -0.07
     terce
    -0.07
     perks
    -0.07
     execut
    -0.07
     быстр
    -0.07
     chance
    -0.07
    POSITIVE LOGITS
     unspecified
    0.09
     quelcon
    0.08
    ità
    0.08
     Goat
    0.08
     தெரிய
    0.08
    _PLACE
    0.08
    未知
    0.08
     thiếu
    0.08
     lat
    0.07
     irgend
    0.07
    Act Density 0.042%

    No Known Activations