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

    Neuronpedia

    INDEX
    Explanations

    artstation.com

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eben
    0.77
    𝙙
    0.76
     aig
    0.74
    िक
    0.73
    𝖽
    0.71
    of
    0.68
     reten
    0.68
     cham
    0.67
     eigenvector
    0.66
    𝟎
    0.66
    POSITIVE LOGITS
     bothered
    0.84
     расположение
    0.81
    перед
    0.76
     вико
    0.72
    felter
    0.72
     illness
    0.70
    轮胎
    0.69
    ៊
    0.69
     домаћинствима
    0.69
     पहले
    0.68
    Act Density 0.003%

    No Known Activations