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

    Neuronpedia

    INDEX
    Explanations

    list structure or factual information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scape
    0.71
    keb
    0.69
     snappy
    0.69
     어느
    0.68
    lös
    0.68
     cleanse
    0.67
    aná
    0.67
     colorful
    0.66
    på
    0.66
     discharged
    0.65
    POSITIVE LOGITS
    辉
    0.79
     estudios
    0.77
    ០០
    0.76
    是一家
    0.75
    在那里
    0.75
    ມັນ
    0.74
    ;%%
    0.74
    쩐
    0.74
    おう
    0.73
    IEF
    0.73
    Act Density 0.001%

    No Known Activations