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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing efficiency and ethics

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

    "as ... as possible"

    np_acts-logits-general · gemini-2.0-flash

    as much as possible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Necessary
    -0.59
     necesario
    -0.57
    Vaata
    -0.57
     Necessary
    -0.55
     مشين
    -0.54
    SuspendLayout
    -0.54
    헌
    -0.54
    posedge
    -0.53
     neceffary
    -0.53
     gereken
    -0.53
    POSITIVE LOGITS
     pos
    1.01
     po
    0.78
     Pos
    0.77
     poss
    0.73
    Pos
    0.70
    pos
    0.66
    tagHelperRunner
    0.66
     practical
    0.63
     Po
    0.62
     POS
    0.62
    Act Density 0.167%

    No Known Activations