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

    Neuronpedia

    INDEX
    Explanations

    headlines and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offici
    0.44
    arakat
    0.43
     alınan
    0.43
    Gas
    0.41
     impug
    0.40
     hó
    0.40
     tokenize
    0.39
     be
    0.39
    till
    0.39
     auß
    0.39
    POSITIVE LOGITS
     старосног
    0.54
     wading
    0.49
     페이지
    0.48
    に適
    0.48
     করতেন
    0.47
     सोबत
    0.47
     ラウンド
    0.46
    UFF
    0.46
     ಇದಕ್ಕೆ
    0.46
     tachycardia
    0.46
    Act Density 0.003%

    No Known Activations