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

    Neuronpedia

    INDEX
    Explanations

    sentences ending or punctuated in a certain way

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

    sentence end punctuation or markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.78
    ⟬
    -0.72
     للمعارف
    -0.70
     يتيمه
    -0.66
     الحره
    -0.66
    InputBorder
    -0.63
     JpaRepository
    -0.62
    MLLoader
    -0.62
     onCancelled
    -0.61
    IntoConstraints
    -0.60
    POSITIVE LOGITS
    !
    0.52
    !).
    0.46
    _.
    0.45
    (!)
    0.44
     (!)
    0.43
    !.
    0.41
     …
    0.41
    .
    0.41
    MD
    0.41
    !)
    0.41
    Act Density 0.086%

    No Known Activations