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

    Neuronpedia

    INDEX
    Explanations

    variations and differences in data sets or populations

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

    differing characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.31
     zieken
    -0.30
     house
    -0.28
     pères
    -0.27
    backButton
    -0.27
     prêtres
    -0.27
     meisje
    -0.26
    ุ่น
    -0.25
     nebo
    -0.25
     pozor
    -0.25
    POSITIVE LOGITS
    цездатний
    0.80
     geſch
    0.74
    Rhestr
    0.73
     deſſen
    0.71
    iſchen
    0.70
     verſch
    0.69
    ⤹
    0.69
     ſehr
    0.69
     beſti
    0.69
    ſicht
    0.69
    Act Density 0.126%

    No Known Activations