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

    Neuronpedia

    INDEX
    Explanations

    malware classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ར
    0.43
    མ
    0.42
    付属
    0.38
    蓽
    0.38
    ('',
    0.37
     interrupted
    0.37
     tubular
    0.37
     druk
    0.36
     cil
    0.36
     sop
    0.35
    POSITIVE LOGITS
    供应链
    0.41
     گزشتہ
    0.40
    पिछले
    0.40
    Weyl
    0.39
     Wrapper
    0.38
    Khi
    0.38
    治理
    0.38
    Alger
    0.38
    标准
    0.38
    资金
    0.38
    Act Density 0.000%

    No Known Activations