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

    Neuronpedia

    INDEX
    Explanations

    technical terms and acronyms related to specific fields or processes

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

    resembling file extensions

    np_acts-logits-general · gemini-2.0-flash

    abbreviations, acronyms, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.59
    er
    -0.58
    javax
    -0.49
    \"");
    -0.47
    >");
    -0.46
    <h2>
    -0.46
    .”.
    -0.45
     "";
    -0.45
    are
    -0.43
    ain
    -0.43
    POSITIVE LOGITS
     lp
    0.74
     Jep
    0.74
     Kip
    0.73
     afp
    0.71
     Dp
    0.70
     Lp
    0.70
     yp
    0.69
     oop
    0.69
     tp
    0.69
     dp
    0.69
    Act Density 1.943%

    No Known Activations