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

    Neuronpedia

    INDEX
    Explanations

    references to figures and illustrations in the text

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

    headings with letters like (a) or (A)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.50
     Italij
    -0.47
    ruik
    -0.46
    ༘
    -0.45
     enamorado
    -0.44
     Privacidad
    -0.43
     paixão
    -0.43
     gehouden
    -0.42
     personalidade
    -0.42
    GGLE
    -0.41
    POSITIVE LOGITS
    ContentAsync
    0.54
     linkovi
    0.45
    SequentialGroup
    0.43
    MatIconModule
    0.40
    IconModule
    0.39
     Perſ
    0.39
    elemField
    0.38
     leſs
    0.38
     ſta
    0.37
     Houſe
    0.37
    Act Density 0.203%

    No Known Activations