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

    Neuronpedia

    INDEX
    Explanations

    what kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بما
    0.35
     آنچه
    0.33
    為何
    0.29
     whats
    0.29
    uela
    0.29
    yler
    0.28
     अनेक
    0.28
     fazendo
    0.28
     kogu
    0.28
     sebagian
    0.28
    POSITIVE LOGITS
     kind
    0.80
     kinds
    0.67
     sort
    0.63
    kind
    0.61
     ধরনের
    0.53
    样的
    0.52
    sort
    0.52
     KIND
    0.49
    kinds
    0.49
     sorts
    0.48
    Act Density 0.117%

    No Known Activations