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

    Neuronpedia

    INDEX
    Explanations

    `only(` or `how humans`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ym
    0.52
    across
    0.48
    越
    0.47
    ös
    0.47
    。
    0.47
     a
    0.46
    function
    0.45
    let
    0.45
    rels
    0.45
    /
    0.45
    POSITIVE LOGITS
     আমাদের
    0.59
     ﺍﻟ
    0.57
     potenza
    0.56
     igual
    0.55
     ﺍ
    0.54
     alamy
    0.54
     আমরা
    0.52
    ಟ್
    0.52
     wzrost
    0.52
     APPE
    0.52
    Act Density 0.000%

    No Known Activations