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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers related to academic papers or research publications

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

    Characters before parentheses

    np_acts-logits-general · gemini-2.0-flash

    URLs and DOIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused16>
    -0.75
    <pad>
    -0.75
    <unused23>
    -0.75
    <unused74>
    -0.75
    <unused43>
    -0.75
    <unused14>
    -0.75
    <unused51>
    -0.75
    <unused52>
    -0.75
    [@BOS@]
    -0.75
    <unused8>
    -0.75
    POSITIVE LOGITS
     announced
    0.35
    .
    0.34
     становника
    0.34
     submissions
    0.34
    BufferException
    0.32
     Fink
    0.32
    tangentMode
    0.32
    </em>
    0.31
     Announced
    0.31
    发表于
    0.31
    Act Density 0.776%

    No Known Activations