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

    Neuronpedia

    INDEX
    Explanations

    scams and attacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pyridazine
    0.86
    स्पे
    0.77
    rystall
    0.76
    isRequired
    0.74
    荷重
    0.74
    ustainability
    0.73
    补偿
    0.73
    umlahan
    0.73
     Simplifying
    0.72
     overshoot
    0.70
    POSITIVE LOGITS
     malicious
    1.95
     nefarious
    1.90
     unscrupulous
    1.88
     fraudulently
    1.85
     malware
    1.81
     maliciously
    1.80
     fraudulent
    1.77
     illegally
    1.73
     criminals
    1.64
     illicit
    1.64
    Act Density 1.580%

    No Known Activations