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

    Neuronpedia

    INDEX
    Explanations

    not necessarily, harmful, or ideal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grainy
    0.47
     настолько
    0.47
     foggy
    0.46
     طور
    0.45
     நுரைய
    0.44
     अभ्यर्थी
    0.44
    込んで
    0.42
     اید
    0.42
     الاض
    0.42
     казни
    0.41
    POSITIVE LOGITS
    _
    0.52
     Series
    0.50
    vi
    0.50
    Series
    0.46
    \
    0.46
     gratuitement
    0.43
     CHA
    0.42
    ɑ
    0.41
    cra
    0.41
     സ്ത്രീ
    0.41
    Act Density 0.005%

    No Known Activations