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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quantities or amounts associated with resources or effects

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

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.81
     EconPapers
    -0.73
    ThroughAttribute
    -0.70
     étoient
    -0.65
     ujednoznacz
    -0.65
    rrggbb
    -0.65
    UserScript
    -0.63
     avoient
    -0.62
    ItemBackground
    -0.61
    ----</
    -0.60
    POSITIVE LOGITS
    Slf
    0.36
    Instead
    0.36
    [...]
    0.35
     afterwards
    0.35
    if
    0.35
    While
    0.35
     Exacts
    0.35
    깐
    0.34
    And
    0.34
     while
    0.34
    Act Density 0.012%

    No Known Activations