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

    Neuronpedia

    INDEX
    Explanations

    all-around, all-in-one

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ungnya
    0.41
    Ტ
    0.40
    堈
    0.39
    閏
    0.35
    ariamente
    0.35
    匝
    0.34
    깥
    0.34
    딧
    0.34
    唁
    0.34
     coeff
    0.34
    POSITIVE LOGITS
    rounder
    0.65
     All
    0.65
     encompassing
    0.64
    purpose
    0.62
    Purpose
    0.57
     Purpose
    0.57
     inclusive
    0.57
    inclusive
    0.56
    compassing
    0.55
     purpose
    0.55
    Act Density 0.009%

    No Known Activations