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

    Neuronpedia

    INDEX
    Explanations

    getting access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मारी
    0.43
     mengikuti
    0.40
     கொண்டிருந்த
    0.40
     पढ़िए
    0.40
     ভারতীয়রা
    0.39
    ajima
    0.39
     Strept
    0.38
    [:-
    0.38
     Prz
    0.38
    ʔ
    0.38
    POSITIVE LOGITS
    十大
    0.39
    くらい
    0.38
     Towards
    0.38
    ές
    0.38
    這邊
    0.38
     everything
    0.37
     retry
    0.37
     whats
    0.37
    送信
    0.37
     alles
    0.36
    Act Density 0.000%

    No Known Activations