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

    Neuronpedia

    INDEX
    Explanations

    allegedly illegal activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podem
    0.62
     മികച്ച
    0.61
     உங்கள்
    0.58
     graceful
    0.57
     możemy
    0.57
     comes
    0.55
     உலக
    0.55
     നിങ്ങളുടെ
    0.54
     gracefully
    0.54
     puedes
    0.53
    POSITIVE LOGITS
     allegedly
    1.02
     illegally
    0.99
     fraudulently
    0.94
     unlawfully
    0.91
     unlawful
    0.85
     alleged
    0.77
     buvo
    0.76
     unauthorized
    0.75
     defendants
    0.75
     fraudulent
    0.73
    Act Density 0.044%

    No Known Activations