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

    Neuronpedia

    INDEX
    Explanations

    knowledge cutoff date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nie
    0.82
     Rxe
    0.81
    enums
    0.79
    くれる
    0.79
    ສາ
    0.75
     Sparse
    0.75
    ኪ
    0.74
    laşt
    0.72
    enje
    0.72
    顷
    0.72
    POSITIVE LOGITS
    tolerance
    0.88
     allotments
    0.82
    $=\
    0.80
    Castro
    0.76
     mực
    0.75
    caution
    0.74
    BoxLayout
    0.74
     الدراسي
    0.72
     lleg
    0.72
    polyline
    0.71
    Act Density 0.169%

    No Known Activations