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

    Neuronpedia

    INDEX
    Explanations

    confidence intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    関節
    0.55
    ccncc
    0.52
    ალური
    0.50
     separable
    0.49
    撣
    0.49
    ಟ್‌
    0.47
    苒
    0.47
    嬠
    0.46
    artition
    0.46
     exemption
    0.46
    POSITIVE LOGITS
     pozy
    0.59
     egy
    0.57
     at
    0.56
    sz
    0.56
     yeni
    0.55
     de
    0.55
    ки
    0.55
     approche
    0.54
     Ingersoll
    0.53
     langt
    0.52
    Act Density 0.001%

    No Known Activations