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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong opinions or feelings

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

    "Really" followed by an emotion word

    np_acts-logits-general · gemini-2.0-flash

    intensifies following words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.69
     ovviamente
    -0.66
    rsiniz
    -0.66
    니다
    -0.64
    Datuak
    -0.63
     forcément
    -0.62
     sicuramente
    -0.61
     umumnya
    -0.59
     certamente
    -0.58
     NOC
    -0.58
    POSITIVE LOGITS
     estate
    0.82
    keits
    0.69
     Estate
    0.66
    ngOnInit
    0.64
     ought
    0.64
    ibatis
    0.63
     REALLY
    0.61
    (!__
    0.58
     nice
    0.57
    estate
    0.55
    Act Density 0.060%

    No Known Activations