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

    Neuronpedia

    INDEX
    Explanations

    that's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.59
    ↵↵
    0.57
    A
    0.50
     Dieser
    0.49
    H
    0.48
    ು
    0.47
     இந்த
    0.47
    L
    0.46
    (
    0.46
     Denne
    0.45
    POSITIVE LOGITS
    zelfde
    0.75
     pesky
    0.59
    רי
    0.52
     is
    0.52
     heißt
    0.52
     séptimo
    0.50
    ляма
    0.45
     звук
    0.44
     случилось
    0.44
    न्या
    0.43
    Act Density 0.060%

    No Known Activations