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

    Neuronpedia

    INDEX
    Explanations

    malware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Это
    0.46
    マスク
    0.45
     moderated
    0.44
    Hmm
    0.43
    모
    0.42
    冖
    0.42
    measures
    0.42
    Excess
    0.41
     تواند
    0.41
    পৃথ
    0.41
    POSITIVE LOGITS
     Mal
    0.81
     mal
    0.73
     MAL
    0.71
    Mal
    0.59
     مال
    0.54
     মাল
    0.48
     मालिनी
    0.47
     Malang
    0.47
     Malin
    0.47
    volent
    0.46
    Act Density 0.011%

    No Known Activations