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

    Neuronpedia

    INDEX
    Explanations

    phrases related to medical trial results and statistics

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

    Numbers or roman numerals

    np_acts-logits-general · gemini-2.0-flash

    numbers (especially 88, 3, 4)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.94
    ParallelGroup
    -0.72
    DoubleQuotes
    -0.68
    DockStyle
    -0.68
     CanadaChoose
    -0.64
    Tembelea
    -0.62
    UserScript
    -0.60
     Fifth
    -0.60
    oneofs
    -0.59
    Fifth
    -0.57
    POSITIVE LOGITS
    3
    0.66
     XXXIV
    0.64
     '\\;'
    0.60
     архивлан
    0.58
     III
    0.55
     three
    0.53
    ₃
    0.52
    🥉
    0.50
     Three
    0.50
     thirties
    0.49
    Act Density 0.492%

    No Known Activations