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

    Neuronpedia

    INDEX
    Explanations

    avoid fraud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nouvelle
    0.38
     लेखन
    0.37
     nouvelles
    0.36
     تاریخ
    0.36
     intercultural
    0.36
     altre
    0.35
     Šk
    0.35
     ท
    0.34
     spiritual
    0.34
     çalışmalar
    0.34
    POSITIVE LOGITS
     defraud
    0.45
     avoid
    0.44
     overpriced
    0.39
    avoid
    0.39
     fraudulently
    0.38
     menghindari
    0.38
     disinfect
    0.38
     मुफ्त
    0.38
    َوْ
    0.37
     sacrificed
    0.36
    Act Density 0.002%

    No Known Activations