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

    Neuronpedia

    INDEX
    Explanations

    malicious and malware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Excessive
    0.41
    aporation
    0.41
    utcnow
    0.40
    ellation
    0.39
    ymethyl
    0.38
    大力
    0.38
    IONI
    0.38
    鈿
    0.38
    excess
    0.38
     मिताली
    0.38
    POSITIVE LOGITS
     Mal
    0.88
    Mal
    0.83
     mal
    0.82
     MAL
    0.81
    mal
    0.71
    ware
    0.65
     Malware
    0.64
    MAL
    0.63
    efic
    0.63
     مال
    0.61
    Act Density 0.014%

    No Known Activations