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

    Neuronpedia

    INDEX
    Explanations

    terms related to research and documentation processes

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

    scientific findings presented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.56
    TagMode
    -0.52
    Aholisi
    -0.49
     Workstation
    -0.46
    itets
    -0.44
     Centa
    -0.44
     
    -0.43
     quint
    -0.42
    bens
    -0.42
    HideFlags
    -0.41
    POSITIVE LOGITS
    BufferException
    0.43
    toHaveBeenCalled
    0.41
     XCTest
    0.40
     ligiloj
    0.40
    migrationBuilder
    0.39
     also
    0.38
     banget
    0.38
    AddRef
    0.36
     meanwhile
    0.36
    oredCriteria
    0.36
    Act Density 0.189%

    No Known Activations