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

    Neuronpedia

    INDEX
    Explanations

    the word "one"

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

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    merie
    -0.41
    ValueStyle
    -0.40
    SCAPE
    -0.40
    Deals
    -0.35
    Disposable
    -0.34
    पया
    -0.34
    さで
    -0.34
     épaules
    -0.34
    setValues
    -0.33
    ürze
    -0.33
    POSITIVE LOGITS
     some
    0.56
    HasOne
    0.52
     ब्रेकडाउन
    0.51
     cualquiera
    0.50
     another
    0.50
     each
    0.49
    المناصب
    0.49
     noDo
    0.48
     synonym
    0.48
     MonoBehaviour
    0.48
    Act Density 0.049%

    No Known Activations