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

    Neuronpedia

    INDEX
    Explanations

    malicious software and resumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usel
    0.53
    する場合は
    0.52
    saldo
    0.50
    elernt
    0.49
    íte
    0.48
    鏁
    0.48
    する場合
    0.47
     الطالب
    0.47
     použit
    0.46
    ைச்
    0.46
    POSITIVE LOGITS
     Floating
    0.45
     million
    0.44
     Stout
    0.43
     swan
    0.43
     breakthrough
    0.42
     preven
    0.41
     beloved
    0.40
    浮
    0.40
     rsp
    0.40
    floating
    0.39
    Act Density 0.000%

    No Known Activations