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

    Neuronpedia

    INDEX
    Explanations

    references to educational activities and student engagement

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

    context after "in? "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.59
     betweenstory
    -0.55
    <unused47>
    -0.50
     torchvision
    -0.50
    <unused51>
    -0.49
    <unused8>
    -0.49
    <unused16>
    -0.49
    <unused41>
    -0.49
    <unused14>
    -0.49
    [@BOS@]
    -0.49
    POSITIVE LOGITS
    addCriterion
    0.41
    Espèce
    0.38
    GOTREF
    0.37
    สึก
    0.37
    Ingrédients
    0.33
    andet
    0.33
     gerekiyor
    0.33
     lenta
    0.33
    //
    0.33
    Ingredienti
    0.32
    Act Density 0.046%

    No Known Activations