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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or behaviors related to justification and responsibility

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

    by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.43
     centrif
    -0.41
     potions
    -0.41
    erapeutics
    -0.40
     diagnostics
    -0.40
     محفوظة
    -0.40
     refinements
    -0.39
    IUrlHelper
    -0.38
    XtraReports
    -0.37
    omock
    -0.36
    POSITIVE LOGITS
    دانشنامهٔ
    0.52
     اینکه
    0.47
     مشين
    0.47
     faptul
    0.46
    ">//
    0.42
     entrust
    0.42
    ftagPool
    0.41
    }}]{
    0.40
    coço
    0.40
     surla
    0.40
    Act Density 0.063%

    No Known Activations