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

    Neuronpedia

    INDEX
    Explanations

    big data, via, analysis, sensitive, dividing, ignores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tamanho
    0.73
     stellte
    0.73
     pagar
    0.73
    مون
    0.72
    postos
    0.71
     bins
    0.71
     بط
    0.70
     sposob
    0.70
    ﻤ
    0.69
     パンツ
    0.68
    POSITIVE LOGITS
    read
    0.89
    NAP
    0.84
    SH
    0.82
    NA
    0.80
    Trademark
    0.79
    LDA
    0.76
    LP
    0.75
    0.75
    NK
    0.74
    NST
    0.74
    Act Density 0.005%

    No Known Activations