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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or studies

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

    links and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.72
    <unused68>
    -0.69
    <unused14>
    -0.69
    <unused8>
    -0.68
    <unused28>
    -0.68
    <pad>
    -0.68
    <unused16>
    -0.68
    <unused23>
    -0.68
    [@BOS@]
    -0.68
    <unused6>
    -0.68
    POSITIVE LOGITS
     initComponents
    0.40
     reverse
    0.35
     AssemblyCulture
    0.34
    audiovisuel
    0.33
    /
    0.32
    Jereo
    0.31
    <u>
    0.30
    </u>
    0.29
     ram
    0.29
    principalTable
    0.28
    Act Density 0.007%

    No Known Activations