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

    Neuronpedia

    INDEX
    Explanations

    highly relevant technical or mathematical terms

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

    French, Spanish, Chinese, and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused74>
    -1.18
    <unused52>
    -1.18
    <unused41>
    -1.18
    [@BOS@]
    -1.17
    <unused28>
    -1.17
    <unused14>
    -1.17
    <unused23>
    -1.17
    <unused16>
    -1.17
    <unused3>
    -1.17
    <unused8>
    -1.17
    POSITIVE LOGITS
    <strong>
    0.30
    <eos>
    0.30
    Đ
    0.28
     vôtre
    0.27
     incluido
    0.26
     citada
    0.26
    <em>
    0.25
    　　
    0.22
     âme
    0.22
     Turquie
    0.21
    Act Density 0.433%

    No Known Activations