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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and proper nouns

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

    Tuscaloosa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tää
    -0.42
    områ
    -0.38
     erbjud
    -0.36
    scenarios
    -0.35
     hoeft
    -0.34
    scenario
    -0.34
    </tfoot>
    -0.34
     scenarios
    -0.34
    <tfoot>
    -0.33
     öppna
    -0.32
    POSITIVE LOGITS
    yama
    0.85
    dafx
    0.79
    caloosa
    0.75
     Covington
    0.75
    manjaro
    0.69
    ristown
    0.66
    itest
    0.65
    batik
    0.63
    avanaugh
    0.60
    illin
    0.59
    Act Density 0.007%

    No Known Activations