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

    Neuronpedia

    INDEX
    Explanations

    distance from shore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻊ
    0.51
    乸
    0.44
     henkil
    0.42
     عادة
    0.41
    Vater
    0.41
    .
    0.41
    自由
    0.40
     recebe
    0.39
     sün
    0.39
    schl
    0.39
    POSITIVE LOGITS
    நுட்ப
    0.49
     in
    0.49
     IN
    0.48
     proves
    0.48
     Tripp
    0.47
     दीप
    0.47
    AtIndexPath
    0.46
    abha
    0.46
    istocene
    0.46
     Bright
    0.46
    Act Density 0.000%

    No Known Activations