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

    Neuronpedia

    INDEX
    Explanations

    clarity in instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙠
    0.80
    𝙜
    0.75
    czyć
    0.69
    ក្នុង
    0.64
    డీపీ
    0.63
     τότε
    0.62
    ຖືກ
    0.61
     алге
    0.60
     tất
    0.59
    calar
    0.59
    POSITIVE LOGITS
    ID
    0.82
    ap
    0.80
    id
    0.74
    IA
    0.73
    on
    0.71
    io
    0.71
    ad
    0.70
    Il
    0.68
    im
    0.65
    ın
    0.65
    Act Density 0.003%

    No Known Activations