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

    Neuronpedia

    INDEX
    Explanations

    quantitative metrics related to data transmission and performance evaluation

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

    followed by "of" that quantify something

    np_acts-logits-general · gemini-2.0-flash

    rate, ratio, levels, value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.61
     GoogleFonts
    -0.58
     Khas
    -0.56
    kkelijk
    -0.56
    FormTagHelper
    -0.56
     TextAppearance
    -0.56
     snippetHide
    -0.54
    horst
    -0.53
    demies
    -0.53
    fusc
    -0.53
    POSITIVE LOGITS
     rate
    1.11
     levels
    1.11
     level
    1.05
     ratio
    0.98
     rates
    0.92
     rating
    0.84
    levels
    0.84
    rate
    0.81
     LEVELS
    0.79
     value
    0.78
    Act Density 1.324%

    No Known Activations