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

    Neuronpedia

    INDEX
    Explanations

    commit a crime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     řek
    0.57
     Itália
    0.52
     powied
    0.51
    ي
    0.51
    দের
    0.50
     Metabol
    0.49
    ையிலும்
    0.48
     imati
    0.48
    يارات
    0.48
     Pedra
    0.48
    POSITIVE LOGITS
    ifting
    0.59
     вас
    0.54
    ass
    0.52
    ﻗ
    0.51
    ency
    0.50
     स्वरुप
    0.49
    お客様
    0.48
     உயரம்
    0.48
     அதனால்
    0.48
     тих
    0.48
    Act Density 0.000%

    No Known Activations