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

    Neuronpedia

    INDEX
    Explanations

    curly braces used in LaTeX document formatting

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

    Code or LaTeX markup

    np_acts-logits-general · gemini-2.0-flash

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.16
    <unused41>
    -1.02
    [@BOS@]
    -1.01
    <unused3>
    -1.01
    <unused42>
    -1.01
    <unused47>
    -1.01
    <unused28>
    -1.01
    <unused21>
    -1.01
    <unused14>
    -1.01
    <unused17>
    -1.01
    POSITIVE LOGITS
     l
    0.29
    ↵↵
    0.28
    ，
    0.27
    <eos>
    0.26
     We
    0.26
     Ch
    0.26
     pendukung
    0.26
    We
    0.25
    A
    0.25
    Ch
    0.25
    Act Density 0.007%

    No Known Activations