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

    Neuronpedia

    INDEX
    Explanations

    time and improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.55
    ﺘ
    0.50
    на
    0.49
     właśnie
    0.49
    jenigen
    0.49
     sogenannten
    0.48
    িক
    0.47
    کي
    0.45
    و
    0.43
     verwend
    0.43
    POSITIVE LOGITS
    you
    0.51
    0.48
    IL
    0.46
     femenino
    0.42
    Recommendations
    0.42
     किंवा
    0.41
    yards
    0.41
     NCBI
    0.41
    ibuya
    0.41
     questionnaire
    0.40
    Act Density 0.168%

    No Known Activations