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

    Neuronpedia

    INDEX
    Explanations

    elements of self-awareness and character introspection

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

    describes literary works and their creators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.72
    +#+#
    -0.63
    awtextra
    -0.61
    transQ
    -0.60
     propOrder
    -0.56
     AssemblyTitle
    -0.56
     resourceCulture
    -0.56
    ----</
    -0.55
     autorytatywna
    -0.54
    VersionUID
    -0.53
    POSITIVE LOGITS
     genre
    0.37
     постанов
    0.35
    manus
    0.33
    asil
    0.32
    LEncoder
    0.31
     Genre
    0.31
     pen
    0.31
     clue
    0.30
    Reg
    0.30
     LOT
    0.30
    Act Density 0.590%

    No Known Activations