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

    Neuronpedia

    INDEX
    Explanations

    prominent punctuation or sentence structure markers in the text

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

    foreign words or conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.71
     <<<<<<<<<<<<<<
    -0.68
    :✨
    -0.67
     BoxDecoration
    -0.66
    minecraftforge
    -0.65
    MemoryWarning
    -0.65
    Diweddarwch
    -0.64
     Administrativna
    -0.63
    httphttps
    -0.63
    Datuak
    -0.63
    POSITIVE LOGITS
     aldri
    0.35
     Daß
    0.32
     którzy
    0.31
     aikana
    0.31
     gjelder
    0.30
     daß
    0.30
     Kontrolle
    0.30
    retudo
    0.28
     Fuß
    0.28
     istrinya
    0.28
    Act Density 0.105%

    No Known Activations