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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and places

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

    References, often with bracketed numbers or author names

    np_acts-logits-general · gemini-2.0-flash

    authors' surnames in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retudo
    -0.44
    पया
    -0.41
     páss
    -0.40
     caminh
    -0.40
     IBOutlet
    -0.39
    dillas
    -0.39
    argout
    -0.37
     olho
    -0.37
    بوابة
    -0.37
     pelúcia
    -0.36
    POSITIVE LOGITS
    zA
    0.56
    TagMode
    0.53
    ValueStyle
    0.52
    usercontent
    0.52
    Будь
    0.50
     Akufo
    0.50
    transQ
    0.50
    Revenir
    0.50
     enfans
    0.49
    KEYCODE
    0.48
    Act Density 0.916%

    No Known Activations