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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements, particularly parentheses and braces

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

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused74>
    -1.06
    <unused28>
    -1.06
    <unused14>
    -1.06
    <pad>
    -1.05
    <unused23>
    -1.05
    <unused8>
    -1.05
    <unused17>
    -1.05
    <unused16>
    -1.05
    [@BOS@]
    -1.05
    <unused3>
    -1.05
    POSITIVE LOGITS
     başlad
    0.38
    .
    0.34
     is
    0.32
    '
    0.32
    bebasan
    0.30
     &
    0.29
    2
    0.29
    1
    0.29
    </td>
    0.29
    3
    0.28
    Act Density 0.001%

    No Known Activations