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

    Neuronpedia

    INDEX
    Explanations

    JSON structures and syntax elements

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

    German and archaic English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.40
     perigo
    -0.34
     peligro
    -0.33
     gruesa
    -0.33
     ganas
    -0.33
     plateado
    -0.33
     adecu
    -0.33
     Besch
    -0.32
     renforcé
    -0.32
    ข
    -0.32
    POSITIVE LOGITS
     poffe
    0.71
     ſta
    0.71
    ſelves
    0.66
     leaſt
    0.64
     ſch
    0.64
     viſ
    0.64
     fubject
    0.63
     Chrift
    0.63
     $_"
    0.63
    ſelf
    0.62
    Act Density 0.110%

    No Known Activations