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

    Neuronpedia

    INDEX
    Explanations

    finding lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ázky
    0.43
    清单
    0.42
    名单
    0.41
    你说
    0.41
     beginnetje
    0.41
    のお知らせ
    0.41
    藠
    0.41
     исследования
    0.41
    原始内容存档
    0.41
     చెప్పు
    0.41
    POSITIVE LOGITS
     pla
    0.42
     feel
    0.39
    want
    0.39
    8
    0.39
     want
    0.38
     Tact
    0.38
    fifth
    0.37
     e
    0.37
    Per
    0.37
    zens
    0.37
    Act Density 0.000%

    No Known Activations