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

    Neuronpedia

    INDEX
    Explanations

    economics, probability, entropy, astrology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    มี
    0.63
    ASTIC
    0.61
    阠
    0.61
    茟
    0.60
    은
    0.59
    ಿರುವ
    0.59
    로운
    0.57
    非法
    0.57
    ใหญ
    0.56
     โร
    0.56
    POSITIVE LOGITS
    .
    0.79
    ни
    0.61
     характера
    0.60
    ра
    0.60
     that
    0.59
    :
    0.59
    ми
    0.58
    ov
    0.57
     which
    0.56
    ᖓ
    0.56
    Act Density 3.071%

    No Known Activations