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

    Neuronpedia

    INDEX
    Explanations

    keywords related to quantitative data analysis methods

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

    Non-English words, code, and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.74
    }))
    -0.67
     pleaſure
    -0.66
     étoient
    -0.65
     Theſe
    -0.64
     faſt
    -0.64
     ſche
    -0.64
     feroit
    -0.63
     myſelf
    -0.62
     leaſt
    -0.62
    POSITIVE LOGITS
     समीक्षाएं
    0.73
    gnancy
    0.70
    Kanpo
    0.68
    HasBeenSet
    0.66
    AutoScaleMode
    0.66
    Collegamenti
    0.65
    awakeFromNib
    0.65
     فريبيس
    0.65
    providedIn
    0.65
    addCriterion
    0.64
    Act Density 0.888%

    No Known Activations