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

    Neuronpedia

    INDEX
    Explanations

    pandas dataframe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adanya
    2.02
    ल
    1.99
    те
    1.96
    tanto
    1.90
    tch
    1.87
    на
    1.84
    tak
    1.83
    té
    1.80
    tener
    1.80
    ták
    1.79
    POSITIVE LOGITS
     Dull
    1.89
     conceivable
    1.79
    Вы
    1.72
    Я
    1.67
    ين
    1.65
    Ли
    1.64
     presume
    1.60
     rightly
    1.56
     doubtful
    1.55
     dedicate
    1.55
    Act Density 0.016%

    No Known Activations