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

    Neuronpedia

    INDEX
    Explanations

    actions related to making decisions or taking initiatives

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

    initiate action or change state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solidif
    -0.47
     Reisedaten
    -0.46
    BrowserModule
    -0.46
    Soli
    -0.45
    avid
    -0.45
     ceilings
    -0.45
     Mastery
    -0.43
    pointments
    -0.42
    NamedQueries
    -0.42
     Essentials
    -0.41
    POSITIVE LOGITS
     anstatt
    0.52
     instead
    0.52
    WithIOException
    0.47
     lieber
    0.44
     rather
    0.44
    instead
    0.43
    脚注の使い方
    0.43
    ScopeManager
    0.42
    TestingModule
    0.41
    帖最后由
    0.41
    Act Density 0.032%

    No Known Activations