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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down" and its variations

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

    handed down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    typeorm
    -0.33
     propOrder
    -0.32
     InputDecoration
    -0.31
    verhältnisse
    -0.31
     nasel
    -0.30
     FetchType
    -0.30
    AddTagHelper
    -0.29
    multirow
    -0.29
    Życiorys
    -0.28
    CompilerServices
    -0.27
    POSITIVE LOGITS
     handed
    0.66
     effortlessly
    0.63
     undisputed
    0.63
     Hands
    0.63
     undeniably
    0.63
    handedly
    0.62
     unequivocally
    0.61
    easily
    0.61
     easily
    0.61
    eniably
    0.60
    Act Density 0.001%

    No Known Activations