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

    Neuronpedia

    INDEX
    Explanations

    documentation URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    quedas
    0.77
    ଦ
    0.76
     wypad
    0.74
    collapse
    0.69
    FullScreen
    0.68
    Huge
    0.67
    ై
    0.67
    Pressure
    0.66
     سعودی
    0.64
     celé
    0.63
    POSITIVE LOGITS
     via
    0.97
     twine
    0.93
    .):
    0.88
     যাবার
    0.88
    :"
    0.86
     nach
    0.84
    uth
    0.84
     osh
    0.83
     über
    0.82
    érir
    0.81
    Act Density 0.016%

    No Known Activations