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

    Neuronpedia

    INDEX
    Explanations

    lists and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    足够
    0.39
     vibration
    0.39
     dź
    0.37
    Rob
    0.37
     NCP
    0.37
    罗斯
    0.37
    ]-->
    0.36
    辅助
    0.36
     quadrant
    0.35
    Lever
    0.35
    POSITIVE LOGITS
    évő
    0.42
     poblaciones
    0.42
    ciente
    0.41
    诰
    0.40
     passi
    0.39
    enov
    0.38
     cuento
    0.38
    ائیگی
    0.38
    cuenta
    0.38
    蛏
    0.38
    Act Density 0.000%

    No Known Activations