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

    Neuronpedia

    INDEX
    Explanations

    scam baiting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Tables
    -0.08
     devoid
    -0.08
    _builtin
    -0.08
     Lif
    -0.08
     확인
    -0.08
     പരിശോധ
    -0.08
     podium
    -0.08
     widths
    -0.07
     관한
    -0.07
     confirms
    -0.07
    POSITIVE LOGITS
     malicious
    0.13
     stealth
    0.11
     deception
    0.10
     phishing
    0.10
     deceptive
    0.10
    攻击
    0.10
    欺
    0.10
     defensive
    0.10
    Feign
    0.10
     malware
    0.09
    Act Density 0.009%

    No Known Activations