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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or assurances in statements

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

    assurance and guarantees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vecino
    -0.57
     venons
    -0.56
    expandindo
    -0.56
     Pingback
    -0.54
    Geography
    -0.54
    ⓧ
    -0.52
    ⵌ
    -0.52
    geography
    -0.51
    europe
    -0.51
    Aiheesta
    -0.51
    POSITIVE LOGITS
     assured
    1.20
     assurance
    1.18
     assures
    1.11
     assurances
    1.09
     assure
    1.09
     assuring
    1.06
     Assurance
    1.05
    Assurance
    0.96
    assurance
    0.95
     guaranteed
    0.91
    Act Density 0.009%

    No Known Activations