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

    Neuronpedia

    INDEX
    Explanations

    data structures and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     İng
    0.82
     Emmy
    0.79
    App
    0.74
     Oyun
    0.73
    ের
    0.73
     compartió
    0.72
    snd
    0.71
    ၅
    0.70
    Địa
    0.69
     mutta
    0.68
    POSITIVE LOGITS
    Т
    0.84
    К
    0.80
    ка
    0.77
     Т
    0.76
    오늘
    0.76
     значення
    0.74
     acts
    0.73
     послед
    0.73
     став
    0.73
    и
    0.70
    Act Density 0.000%

    No Known Activations