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

    Neuronpedia

    INDEX
    Explanations

    references to legal codes and regulatory frameworks

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

    following capitalized abbreviations

    np_acts-logits-general · gemini-2.0-flash

    art, Pin, Geom, Bet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -1.67
    <unused28>
    -1.66
    <unused52>
    -1.66
    <unused8>
    -1.66
    <unused74>
    -1.66
    [@BOS@]
    -1.66
    <unused79>
    -1.66
    <unused17>
    -1.66
    <unused16>
    -1.66
    <unused14>
    -1.66
    POSITIVE LOGITS
    (
    0.33
    0
    0.30
    1
    0.29
    V
    0.28
    R
    0.28
    M
    0.26
    Q
    0.26
    \
    0.24
    3
    0.24
    2
    0.24
    Act Density 2.452%

    No Known Activations