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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating reaching or attaining certain limits or milestones

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

    reaching a goal or destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.57
    RefNanny
    -0.41
     guise
    -0.40
     [](
    -0.40
    Slf
    -0.39
     spesso
    -0.38
     tute
    -0.37
     gin
    -0.36
     hinweg
    -0.36
     parlor
    -0.35
    POSITIVE LOGITS
    ElementException
    0.56
    Condiciones
    0.51
    kháu
    0.46
    rungsseite
    0.46
    autoconfigure
    0.44
     Conditions
    0.44
     stade
    0.43
    atteindre
    0.43
    CategoryName
    0.43
     jLabel
    0.43
    Act Density 0.025%

    No Known Activations