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

    Neuronpedia

    INDEX
    Explanations

    achievable at home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    0.43
    anken
    0.43
    erzo
    0.42
    bamos
    0.40
    comedy
    0.40
    ハム
    0.40
    halts
    0.39
    LEMENT
    0.38
    スマス
    0.38
    ordnet
    0.38
    POSITIVE LOGITS
     oreilles
    0.52
     قدیمی
    0.52
     člov
    0.49
     حياة
    0.48
    птова
    0.48
     የበለጠ
    0.48
     توصیه
    0.48
     uncertainties
    0.47
     проще
    0.47
     різ
    0.47
    Act Density 0.000%

    No Known Activations