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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recessed
    0.88
    ковым
    0.88
    xi
    0.86
    nolds
    0.85
    ित्र
    0.84
    '&
    0.83
    喽
    0.82
    či
    0.79
    chen
    0.78
     себя
    0.78
    POSITIVE LOGITS
     ಕ್
    0.97
     ઇ
    0.89
     વખતે
    0.82
    த்
    0.82
     pw
    0.81
    ulaires
    0.80
    ﾜ
    0.80
     ’’
    0.79
     virtuel
    0.79
    なっている
    0.76
    Act Density 0.000%

    No Known Activations