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

    Neuronpedia

    INDEX
    Explanations

    specific technical details related to various formulations and their performance metrics

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

    Numbers followed by a unit, or math

    np_acts-logits-general · gemini-2.0-flash

    numbers and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Requirements
    -0.27
    pezifische
    -0.27
    He
    -0.25
    さまざま
    -0.25
     gef
    -0.25
     Desarrollo
    -0.25
     발
    -0.24
    Dear
    -0.24
    ernoo
    -0.24
    pezif
    -0.23
    POSITIVE LOGITS
    цездатний
    0.68
     للاسماء
    0.66
     préférence
    0.65
     Normdatei
    0.63
     незавершена
    0.62
    OGND
    0.61
    webElementXpaths
    0.61
    moveToFirst
    0.60
    execSQL
    0.58
    LookAnd
    0.58
    Act Density 1.346%

    No Known Activations