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

    Neuronpedia

    INDEX
    Explanations

    metamaterials, Magic, run-length encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occasional
    0.48
     लिमिटेड
    0.45
     indelible
    0.44
     clerk
    0.43
     occasionally
    0.43
     université
    0.42
    ляр
    0.42
     widowed
    0.41
     acquaintance
    0.41
    ኵ
    0.41
    POSITIVE LOGITS
    喍
    0.50
    at
    0.46
    IFIER
    0.46
    tit
    0.46
    hh
    0.45
    ranno
    0.45
    𝙡
    0.45
     ప్రో
    0.44
    Virtualized
    0.43
    lova
    0.43
    Act Density 0.000%

    No Known Activations