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

    Neuronpedia

    INDEX
    Explanations

    software licenses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mars
    -0.75
     Dok
    -0.73
     corazones
    -0.71
    Dok
    -0.70
     terem
    -0.69
     causado
    -0.66
    outer
    -0.66
    jalankan
    -0.66
    推送
    -0.65
    Abend
    -0.65
    POSITIVE LOGITS
    σε
    0.70
    ﻳ
    0.69
    蓉
    0.69
    HALF
    0.68
    Domain
    0.68
    歌手
    0.67
     kelp
    0.67
     turquoise
    0.65
    METHOD
    0.65
     popu
    0.65
    Act Density 0.084%

    No Known Activations