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

    Neuronpedia

    INDEX
    Explanations

    blocks of text in different languages or scripts

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

    Preceding punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    period after "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    -0.81
     T
    -0.79
     I
    -0.77
     
    -0.77
     G
    -0.76
     pre
    -0.76
     H
    -0.76
     g
    -0.76
     Y
    -0.75
     of
    -0.74
    POSITIVE LOGITS
    RenderAtEndOf
    1.19
     дописавши
    1.09
    contentLoaded
    1.05
     незавершена
    1.03
    ьаж
    1.00
    GEBURTSDATUM
    0.97
    AndEndTag
    0.94
     Taktlose
    0.94
     виправивши
    0.93
    Билгалдахарш
    0.93
    Act Density 0.026%

    No Known Activations