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

    Neuronpedia

    INDEX
    Explanations

    origin and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tornar
    0.71
    ад
    0.68
     podendo
    0.66
     devenu
    0.66
    et
    0.65
    و
    0.64
     making
    0.64
    astly
    0.64
     dwa
    0.63
    ्याचा
    0.62
    POSITIVE LOGITS
     fromi
    0.78
    APAN
    0.68
    ialog
    0.65
    uyente
    0.65
    অম
    0.65
     imasmim
    0.65
     Saltar
    0.64
    Trademark
    0.64
    Disagree
    0.64
     किसने
    0.64
    Act Density 0.386%

    No Known Activations