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

    Neuronpedia

    INDEX
    Explanations

    complex data structures and operations related to programming

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

    mathematical expressions and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.66
     Houſe
    -0.59
    majánló
    -0.56
     purpoſe
    -0.55
     Conſ
    -0.54
     houſe
    -0.54
    wiſe
    -0.54
     ſta
    -0.52
    setVerticalGroup
    -0.52
    ſelf
    -0.51
    POSITIVE LOGITS
     ویکی‌پدی
    0.47
    getDoctrine
    0.43
    Хьажоргаш
    0.42
    Abitanti
    0.41
    новниш
    0.40
    expandindo
    0.40
     CanadaChoose
    0.39
    хьтан
    0.38
     uska
    0.38
     هيا
    0.38
    Act Density 0.001%

    No Known Activations