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

    Neuronpedia

    INDEX
    Explanations

    terms related to switching and changing states

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

    changing or switching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tain
    -0.40
    pel
    -0.37
    ItemInfo
    -0.36
     duy
    -0.33
    open
    -0.32
    tin
    -0.31
    msup
    -0.31
    Ona
    -0.30
    istream
    -0.30
     GLO
    -0.30
    POSITIVE LOGITS
     wechseln
    0.67
    ViewImports
    0.65
    Switching
    0.64
     Switching
    0.62
     switching
    0.61
     AssemblyCompany
    0.60
    0.60
     invokingState
    0.59
     changer
    0.59
     newOwner
    0.59
    Act Density 0.055%

    No Known Activations