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

    Neuronpedia

    INDEX
    Explanations

    instances of examples or evidence supporting various points

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

    enumerating examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NamedQueries
    -0.64
     surla
    -0.63
    Jereo
    -0.59
     EconPapers
    -0.59
    MigrationBuilder
    -0.56
     <<<<<<<<<<<<<<
    -0.54
    ArrowToggle
    -0.54
     समीक्षाओं
    -0.54
    RenderAtEndOf
    -0.53
    GEBURTSDATUM
    -0.51
    POSITIVE LOGITS
     examples
    0.75
     ejemplos
    0.61
     EXAMPLES
    0.59
     Beispiele
    0.58
     exemplos
    0.57
     anecdotes
    0.56
     instances
    0.55
     Examples
    0.54
    Beispiele
    0.54
     esempi
    0.54
    Act Density 0.140%

    No Known Activations