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

    Neuronpedia

    INDEX
    Explanations

    Java code imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বৃত্ত
    0.84
    યર
    0.79
     catálogo
    0.78
    LError
    0.77
    liquer
    0.76
     Mansion
    0.75
    ठभे
    0.75
    ﺨ
    0.75
    DVRIP
    0.74
     ".")
    0.73
    POSITIVE LOGITS
     organic
    0.73
     lifecycle
    0.69
     scene
    0.69
     sw
    0.68
     protected
    0.68
     daily
    0.66
     जनजा
    0.66
    σης
    0.66
     частина
    0.66
     sl
    0.65
    Act Density 0.008%

    No Known Activations