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

    Neuronpedia

    INDEX
    Explanations

    prepositions and phrases indicating spatial relationships

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

    prepositions and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.58
     فريبيس
    -0.49
     kasarigan
    -0.46
     torchvision
    -0.42
    %{
    -0.41
     houſe
    -0.41
     ſte
    -0.40
     poffe
    -0.40
    mainloop
    -0.39
     ſp
    -0.39
    POSITIVE LOGITS
    UnusedPrivate
    0.48
    XmlAccessType
    0.46
    chaqueta
    0.46
     tartış
    0.45
     Wikimedijinoj
    0.44
    échelle
    0.44
     praça
    0.44
     alugar
    0.43
     préférence
    0.43
    forth
    0.42
    Act Density 0.002%

    No Known Activations