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

    Neuronpedia

    INDEX
    Explanations

    App imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لە
    1.97
    ﻫ
    1.95
    ل
    1.94
     sute
    1.86
    라
    1.84
    ້ອ
    1.81
     avión
    1.73
    ॠ
    1.73
    рати
    1.73
    LETIN
    1.73
    POSITIVE LOGITS
    <bos>
    1.75
    ﻲ
    1.67
    steal
    1.66
    jammer
    1.61
    yscanner
    1.61
     unmarked
    1.59
     whispered
    1.58
    ى
    1.57
    us
    1.57
     mistaken
    1.56
    Act Density 0.000%

    No Known Activations