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

    Neuronpedia

    INDEX
    Explanations

    structured data language or code syntax elements

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

    Conditional null/None returns

    np_acts-logits-general · gemini-2.0-flash

    else return null/empty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mắn
    -0.41
    ftagPool
    -0.40
    setopt
    -0.39
    [
    -0.39
    rungsseite
    -0.38
    nloa
    -0.38
     >=",
    -0.37
    preuve
    -0.37
    leşti
    -0.36
    irmanship
    -0.36
    POSITIVE LOGITS
    None
    2.10
     None
    2.09
     nothing
    2.09
     null
    2.02
     none
    1.97
    none
    1.92
    null
    1.92
    nothing
    1.90
     Nothing
    1.87
    Nothing
    1.86
    Act Density 0.725%

    No Known Activations