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

    Neuronpedia

    INDEX
    Explanations

    full of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    消失
    0.48
    ປະກອບ
    0.43
    ्युअर
    0.43
    拉斯
    0.41
     සම්
    0.40
    ught
    0.39
    ক্ট
    0.39
    imov
    0.38
    Asalamualaikum
    0.38
    なくな
    0.38
    POSITIVE LOGITS
     value
    0.54
     details
    0.52
     values
    0.50
     months
    0.49
     fuller
    0.49
     vitality
    0.48
     age
    0.48
     valor
    0.47
     minute
    0.46
     FULLER
    0.46
    Act Density 0.001%

    No Known Activations