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

    Neuronpedia

    INDEX
    Explanations

    more complex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chargers
    0.50
     خدمات
    0.49
    جی
    0.47
    演员
    0.47
     Dahmer
    0.46
     servicios
    0.46
    بھی
    0.46
    یوں
    0.45
     jokingly
    0.45
    のご
    0.45
    POSITIVE LOGITS
    н
    0.55
     form
    0.52
    for
    0.52
     форма
    0.52
    ল
    0.47
    n
    0.47
     for
    0.46
    form
    0.45
    revision
    0.45
     fig
    0.44
    Act Density 0.004%

    No Known Activations