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

    Neuronpedia

    INDEX
    Explanations

    array indices and loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Imagery
    0.73
     CATEG
    0.70
     régime
    0.69
    Probit
    0.69
     attribution
    0.69
     imagery
    0.69
     hypertext
    0.66
     vernacular
    0.66
     responding
    0.66
     Kategorie
    0.65
    POSITIVE LOGITS
     nums
    1.40
    nums
    1.36
     subarray
    1.32
     arr
    1.18
    数组
    1.17
    indices
    1.12
    subarray
    1.11
     indices
    1.11
    arr
    1.10
     subarrays
    1.09
    Act Density 1.560%

    No Known Activations