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

    Neuronpedia

    INDEX
    Explanations

    elements related to strategy and deception in conflict scenarios

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

    strategic maneuvers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntOverflow
    -0.33
    fattning
    -0.33
    ciclop
    -0.31
     المعيارى
    -0.31
     considérons
    -0.31
     Morin
    -0.30
    UnitTesting
    -0.30
    asteroide
    -0.29
    chèque
    -0.29
    simum
    -0.29
    POSITIVE LOGITS
     lenker
    0.57
    ">—
    0.49
     ligiloj
    0.48
    تفصیلات
    0.47
    FormTagHelper
    0.47
     hijack
    0.47
    WebVitals
    0.47
    Exeunt
    0.46
     nahilalakip
    0.46
    ValueStyle
    0.45
    Act Density 0.282%

    No Known Activations