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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numeric values or timestamps

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

    sports scores and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ckså
    -0.35
    ;#
    -0.34
    inaires
    -0.32
    }{*}{
    -0.31
     vaste
    -0.31
     плит
    -0.29
    dalen
    -0.29
     дове
    -0.29
     respectively
    -0.28
     lær
    -0.28
    POSITIVE LOGITS
    ReusableCell
    0.75
    intios
    0.64
    Derbyniad
    0.64
     Meksiku
    0.61
    delwed
    0.60
    évaluateur
    0.59
     CreateTagHelper
    0.58
    complexContent
    0.58
     surla
    0.57
     Italijanski
    0.56
    Act Density 0.002%

    No Known Activations