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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with statistical data

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.43
     Infórmanos
    -0.41
     astore
    -0.41
    bain
    -0.40
     AssemblyCulture
    -0.40
     EconPapers
    -0.40
    UserScript
    -0.39
    colgroup
    -0.38
     oldValue
    -0.37
    processData
    -0.37
    POSITIVE LOGITS
    lorette
    0.50
    styleType
    0.45
     Danemark
    0.39
     Wasserstoff
    0.39
     Galilee
    0.39
     maroca
    0.39
    Newport
    0.38
     Allentown
    0.38
     дописавши
    0.38
     isra
    0.38
    Act Density 0.000%

    No Known Activations