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

    Neuronpedia

    INDEX
    Explanations

    rates and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zenesulf
    0.68
     obtuse
    0.67
     Phoenix
    0.67
     CTRL
    0.64
    لیسی
    0.62
     consent
    0.62
     ngại
    0.62
     mean
    0.62
     monthly
    0.61
     sag
    0.61
    POSITIVE LOGITS
    Registro
    0.78
    forter
    0.76
    🖉
    0.75
     ಬಿ
    0.72
    ায
    0.72
     স্থাপত্য
    0.71
    בית
    0.71
     publicité
    0.70
     বিকাশ
    0.70
     السيارة
    0.68
    Act Density 0.001%

    No Known Activations