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

    Neuronpedia

    INDEX
    Explanations

    words that indicate uncertainty or hesitancy

    oai_token-act-pair · gemini-2.0-flash

    qualifiers/hedges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Whilst
    -0.82
     Whilst
    -0.79
    ategorised
    -0.75
     permasalahan
    -0.71
    +#+#
    -0.70
     disant
    -0.67
     predicament
    -0.67
     defStyle
    -0.65
     conoz
    -0.64
     showcasing
    -0.64
    POSITIVE LOGITS
    AlterField
    0.57
     möjligt
    0.55
    Искәрмәләр
    0.55
    ungkinkan
    0.54
    AsUp
    0.52
    ArrowToggle
    0.50
    Diweddarwch
    0.50
     Giuliani
    0.49
     الدولى
    0.48
     BZ
    0.48
    Act Density 2.138%

    No Known Activations