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
    狂
    -0.07
     markup
    -0.07
     divisions
    -0.07
     明
    -0.07
     programme
    -0.07
    lers
    -0.07
    ώνα
    -0.07
     cards
    -0.07
    аны
    -0.06
    กรณ
    -0.06
    POSITIVE LOGITS
    _PRESENT
    0.06
    (...)
    0.06
     diff
    0.06
     gettimeofday
    0.06
    زة
    0.06
    optim
    0.06
    (cuda
    0.06
    (figsize
    0.06
    ов
    0.06
    iVar
    0.06
    Act Density 0.011%

    No Known Activations