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

    Neuronpedia

    INDEX
    Explanations

    references to transparency and visibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    laid-open patent applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.37
     tæ
    -0.35
    KommentareTeilen
    -0.34
     alkot
    -0.32
     Fecha
    -0.31
    UIFont
    -0.31
    Makefile
    -0.30
     etiqueta
    -0.30
     dön
    -0.29
     çık
    -0.29
    POSITIVE LOGITS
     lay
    1.13
     laying
    1.03
    Lay
    1.02
     Lay
    1.02
     lays
    1.01
     laid
    0.99
    laid
    0.99
     LAY
    0.95
    laying
    0.90
     Laid
    0.86
    Act Density 0.021%

    No Known Activations