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

    Neuronpedia

    INDEX
    Explanations

    numerical data representing measurements or values

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

    figure references like g010

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Niles
    -0.40
     fast
    -0.39
     gynhyrchwyd
    -0.38
    …
    -0.35
    òa
    -0.35
    렷
    -0.35
     FAST
    -0.34
    くちゃ
    -0.33
    nowrap
    -0.33
    諏訪
    -0.33
    POSITIVE LOGITS
     GX
    0.77
    :✨
    0.73
     GLC
    0.71
     gx
    0.64
    gds
    0.63
     groupBox
    0.62
     GSC
    0.62
    GX
    0.61
    GC
    0.61
    endregion
    0.61
    Act Density 0.150%

    No Known Activations