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

    Neuronpedia

    INDEX
    Explanations

    rounding to decimal places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     refine
    0.43
     piezas
    0.42
    淺
    0.42
     кусо
    0.41
    更能
    0.38
    混乱
    0.38
     deficient
    0.38
    审美
    0.38
    成績
    0.37
    ℗
    0.37
    POSITIVE LOGITS
    issauga
    0.41
    lum
    0.38
    galaxy
    0.36
     galaxy
    0.35
    enl
    0.35
    #
    0.35
    akun
    0.34
    ibaba
    0.34
     Elasticsearch
    0.34
    >
    0.33
    Act Density 0.000%

    No Known Activations