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

    Neuronpedia

    INDEX
    Explanations

    elements related to JSON syntax or formatting

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

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fillType
    -0.55
     AssemblyCompany
    -0.52
    __*/
    -0.50
    abestanden
    -0.49
     المعيارى
    -0.48
     plane
    -0.47
     OMITBAD
    -0.46
    ագրություններ
    -0.45
    astify
    -0.45
    OGND
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.58
     confiable
    0.49
     didalam
    0.49
    lež
    0.47
    จบ
    0.47
     whilst
    0.45
     Aufla
    0.45
    décoration
    0.45
     Whilst
    0.44
    addContainerGap
    0.44
    Act Density 0.013%

    No Known Activations