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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    readme
    0.57
    読んで
    0.56
    SCRIPT
    0.56
     Schreiben
    0.55
    テキスト
    0.54
     Pledge
    0.53
     Jehová
    0.53
     README
    0.52
     글
    0.52
     BEFORE
    0.52
    POSITIVE LOGITS
     dis
    0.75
     mengalami
    0.66
     diper
    0.63
     disa
    0.63
     Dis
    0.57
     diterapkan
    0.56
     सभी
    0.55
     berada
    0.55
     dig
    0.54
    所有的
    0.54
    Act Density 0.123%

    No Known Activations