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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or assistance provided by an organization

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

    help, listen, court, think, sat, harvest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izr
    -0.43
     volte
    -0.40
    Formazione
    -0.40
     lip
    -0.37
     dipa
    -0.37
    ulity
    -0.37
     Bunk
    -0.37
    ecraft
    -0.36
    ctivity
    -0.36
     Expectations
    -0.36
    POSITIVE LOGITS
     ویکی‌پدی
    0.59
     disambiguazione
    0.51
    UnknownFieldSet
    0.49
    AndEndTag
    0.49
     وتسجيلات
    0.47
    Diweddarwch
    0.45
     noDo
    0.45
     noastre
    0.44
    dafx
    0.44
     help
    0.44
    Act Density 0.011%

    No Known Activations