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

    Neuronpedia

    INDEX
    Explanations

    evaluating options to decide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.93
    ly
    0.73
    می
    0.70
    نه
    0.67
    ing
    0.67
     i
    0.67
    reate
    0.66
    ness
    0.65
    רי
    0.65
    ación
    0.64
    POSITIVE LOGITS
    ك
    1.00
    ка
    0.92
    ла
    0.87
    AR
    0.72
    كين
    0.67
    g
    0.66
     глав
    0.63
    出発
    0.61
    😨
    0.61
    ৰ
    0.60
    Act Density 0.003%

    No Known Activations