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

    Neuronpedia

    INDEX
    Explanations

    scams, fraud, phishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बनाता
    0.59
     ഇത്
    0.54
    精确
    0.54
    Analysis
    0.52
     هذا
    0.51
    Compiled
    0.51
    这将
    0.51
     цього
    0.50
    這是
    0.50
     this
    0.49
    POSITIVE LOGITS
     scammers
    0.71
     scams
    0.66
    害者
    0.59
     antich
    0.58
     scam
    0.57
    วัสดี
    0.54
    แส
    0.54
     outcast
    0.54
    詐
    0.54
     persecution
    0.53
    Act Density 0.076%

    No Known Activations