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

    Neuronpedia

    INDEX
    Explanations

    gratitude expressions and words related to programming or technical subjects

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

    Chinese and Japanese words, proper names, abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     g
    -0.77
    ViewInit
    -0.73
    g
    -0.69
    gs
    -0.67
    gh
    -0.67
    gid
    -0.64
    ga
    -0.63
    ging
    -0.63
    gy
    -0.62
     Gey
    -0.61
    POSITIVE LOGITS
     Touchable
    0.49
    تقاوى
    0.46
    ViewChild
    0.44
    ьаж
    0.43
    awtextra
    0.42
    ?*
    0.42
    *}\
    0.42
    xnn
    0.41
    JsonInclude
    0.41
    DetailComponent
    0.41
    Act Density 0.174%

    No Known Activations