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

    Neuronpedia

    INDEX
    Explanations

    impact of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‍♀️
    2.06
     سازی
    1.79
    Какие
    1.76
    പി
    1.75
    и
    1.74
     irony
    1.72
    k
    1.72
     walang
    1.69
    НГ
    1.66
    ipping
    1.66
    POSITIVE LOGITS
     върху
    2.00
    sofar
    1.84
     воздействия
    1.77
     crater
    1.73
     adversely
    1.72
     marquée
    1.71
     decisively
    1.69
    fillStyle
    1.68
    ahiran
    1.63
    лиз
    1.62
    Act Density 0.467%

    No Known Activations