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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proportions or ratios

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

    x out of y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.52
     Einfluß
    -0.46
    zelfde
    -0.45
    IUrlHelper
    -0.44
     kaarangay
    -0.41
     tartalomajánló
    -0.41
     contemporánea
    -0.40
     líquida
    -0.39
     Bewußt
    -0.39
     plazos
    -0.39
    POSITIVE LOGITS
    insics
    0.47
     franco
    0.47
    DispatchQueue
    0.46
     Jolly
    0.46
     Statistic
    0.46
     Tin
    0.45
     Barry
    0.45
     intStringLen
    0.45
    autoconfigure
    0.44
    marvin
    0.44
    Act Density 0.023%

    No Known Activations