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

    Neuronpedia

    INDEX
    Explanations

    what the hell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ❙
    0.41
    בוה
    0.37
     bist
    0.37
    ណ្ត
    0.36
    展
    0.36
    횡
    0.36
     неви
    0.36
     تیز
    0.35
     কোলে
    0.35
    倨
    0.34
    POSITIVE LOGITS
     hell
    3.20
     heck
    2.98
     Hell
    2.48
    hell
    2.47
    Hell
    2.44
     Heck
    2.28
     fuck
    2.19
    fuck
    1.96
     Fuck
    1.85
    Fuck
    1.84
    Act Density 0.018%

    No Known Activations