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

    Neuronpedia

    INDEX
    Explanations

    Proposition 8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixe
    -0.07
     Ça
    -0.07
    ovo
    -0.07
    nsic
    -0.07
    ći
    -0.06
     craving
    -0.06
     court
    -0.06
    слов
    -0.06
     мне
    -0.06
    [T
    -0.06
    POSITIVE LOGITS
    _shared
    0.07
    (timer
    0.07
    蒸
    0.07
     Lantern
    0.07
     Trainer
    0.07
     Fantasy
    0.07
    觉醒
    0.07
    荣誉
    0.07
    _weights
    0.07
    便利
    0.07
    Act Density 0.002%

    No Known Activations