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

    Neuronpedia

    INDEX
    Explanations

    actions related to control, adjustment, and states of physical objects or entities

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

    stopping, removing, disagreeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dậy
    -0.38
    раздо
    -0.38
     rockets
    -0.38
    黝
    -0.35
    NullException
    -0.32
     grabs
    -0.32
    边界
    -0.32
    DataAnnotations
    -0.32
    预约
    -0.31
     KeyError
    -0.31
    POSITIVE LOGITS
    ConstraintMaker
    0.59
    脚注の使い方
    0.56
    UpDown
    0.54
     resourceCulture
    0.53
    UserScript
    0.53
    webElement
    0.52
     '\\;'
    0.51
     EconPapers
    0.50
    الحياه
    0.49
     חיצוניים
    0.49
    Act Density 0.251%

    No Known Activations