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

    Neuronpedia

    INDEX
    Explanations

    potentially run

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    P
    0.50
    Imperial
    0.50
    Note
    0.49
    Japanese
    0.49
    W
    0.48
    Sh
    0.48
    \
    0.48
     (
    0.47
    </i>
    0.47
     imperial
    0.47
    POSITIVE LOGITS
     জানালা
    0.49
     بغیر
    0.48
     دستی
    0.48
     եւ
    0.48
    ຄ້າ
    0.46
     gestalten
    0.46
     மனு
    0.46
     thérapeutique
    0.46
     contexte
    0.46
    olare
    0.45
    Act Density 0.000%

    No Known Activations