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

    Neuronpedia

    INDEX
    Explanations

    URLs in various formats

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

    URLs after a period

    np_acts-logits-general · gemini-2.0-flash

    urls and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -1.29
    <unused52>
    -1.29
    <unused41>
    -1.29
    <unused42>
    -1.29
    <unused16>
    -1.29
    <unused14>
    -1.29
    <unused23>
    -1.29
    <unused28>
    -1.29
    [@BOS@]
    -1.28
    <unused3>
    -1.28
    POSITIVE LOGITS
    ://
    0.84
     the
    0.52
    www
    0.50
    .
    0.50
    The
    0.47
     "
    0.39
    "
    0.38
    <i>
    0.38
     www
    0.38
     The
    0.38
    Act Density 0.045%

    No Known Activations