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

    Neuronpedia

    INDEX
    Explanations

    terms related to excessive or over-expressive actions and behaviors

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

    excess or overuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Clik
    -0.40
     ͜ʖ
    -0.39
    Chips
    -0.35
    BeNil
    -0.35
    Fun
    -0.35
    칸
    -0.34
    Wpf
    -0.34
     ligiloj
    -0.33
    WRENCE
    -0.33
     */
    -0.32
    POSITIVE LOGITS
     overdose
    0.68
    过度
    0.68
     exces
    0.66
     exceso
    0.66
     excessive
    0.65
     oversized
    0.64
     overworked
    0.64
    Excessive
    0.63
    excess
    0.63
     overweight
    0.63
    Act Density 0.053%

    No Known Activations