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

    Neuronpedia

    INDEX
    Explanations

    conversational conjunctions and transitions that suggest contrast or continuation

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

    foreign technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Anschluss
    -0.36
     Compañ
    -0.34
     romántica
    -0.30
    Pois
    -0.29
     olvido
    -0.29
     conclu
    -0.29
     Walkover
    -0.28
     finos
    -0.28
    makaian
    -0.28
     dele
    -0.28
    POSITIVE LOGITS
    GEBURTS
    0.70
    DockStyle
    0.61
     Drapeau
    0.60
    Hentet
    0.60
    pingente
    0.59
     كومونز
    0.57
     NSCoder
    0.56
    ftagPool
    0.55
    dead
    0.54
    akteur
    0.54
    Act Density 0.021%

    No Known Activations