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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity or obligation

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

    has to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apparaître
    -0.41
    Демографія
    -0.40
    tagez
    -0.37
    tersebut
    -0.37
     ویکی‌پدی
    -0.36
     stockbild
    -0.36
     neige
    -0.36
     הוד
    -0.36
    dyž
    -0.36
     sisält
    -0.36
    POSITIVE LOGITS
    cydow
    0.57
     parseFrom
    0.50
    fastjson
    0.46
    delwed
    0.46
    mtrl
    0.45
    GEBURTSDATUM
    0.44
    AndEndTag
    0.44
     >=",
    0.44
    ьаж
    0.43
     estekak
    0.42
    Act Density 0.019%

    No Known Activations