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

    Neuronpedia

    INDEX
    Explanations

    references to work or school-related activities

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

    work contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -1.02
     nakalista
    -0.67
    AddTagHelper
    -0.65
    Diweddarwch
    -0.64
    RotationOrder
    -0.63
     مشين
    -0.63
     CascadeType
    -0.57
     argint
    -0.56
    Tikang
    -0.56
     Италијани
    -0.56
    POSITIVE LOGITS
     hosp
    0.35
     workday
    0.35
     work
    0.34
     Inst
    0.33
    Inst
    0.32
    sleep
    0.32
     paying
    0.32
     foe
    0.32
    Sta
    0.31
    work
    0.31
    Act Density 0.012%

    No Known Activations