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

    Neuronpedia

    INDEX
    Explanations

    recurring mathematical notation and syntax elements

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

    mathematical variables after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused8>
    -0.94
    <unused28>
    -0.94
    <unused41>
    -0.94
    <unused14>
    -0.94
    <unused43>
    -0.94
    <unused3>
    -0.94
    <unused16>
    -0.94
    <unused68>
    -0.94
    [@BOS@]
    -0.93
    <unused51>
    -0.93
    POSITIVE LOGITS
     justicia
    0.29
     piernas
    0.28
     again
    0.28
     gants
    0.27
     guantes
    0.26
     Inscrivez
    0.26
    .
    0.26
     faveur
    0.25
     voer
    0.25
     deberes
    0.24
    Act Density 0.089%

    No Known Activations