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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords and structures

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

    Code comments: FIXME, TODO, and similar

    np_acts-logits-general · gemini-2.0-flash

    FIXME, TODO, uncomment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.57
     ProtoMessage
    -0.56
     &___
    -0.55
    expandindo
    -0.53
     pinulongan
    -0.52
     iconLine
    -0.52
     EconPapers
    -0.48
     MessageBoxIcon
    -0.48
     estekak
    -0.47
    balleur
    -0.47
    POSITIVE LOGITS
    >-->
    0.63
     uncomment
    0.61
     fubject
    0.52
     FIXME
    0.51
    TODO
    0.49
     TODO
    0.47
     todo
    0.47
    PMailer
    0.45
    lait
    0.44
    todo
    0.43
    Act Density 0.125%

    No Known Activations