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

    Neuronpedia

    INDEX
    Explanations

    gradle build dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ric
    0.64
     û
    0.62
     ù
    0.61
     és
    0.60
     keepsake
    0.59
     și
    0.59
     şi
    0.59
     Columbus
    0.59
     î
    0.58
     ɔ
    0.57
    POSITIVE LOGITS
    ن
    0.75
    $
    0.66
    V
    0.66
    期待
    0.61
    P
    0.60
    F
    0.60
    Л
    0.59
    T
    0.58
    Ч
    0.58
    Щ
    0.58
    Act Density 0.005%

    No Known Activations