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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming code and syntax

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

    Code snippets or URLs

    np_acts-logits-general · gemini-2.0-flash

    code and web addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jeografia
    -0.42
    новниш
    -0.35
    webElementXpaths
    -0.34
     substituted
    -0.29
    öße
    -0.29
     straips
    -0.27
    IntoConstraints
    -0.27
     sums
    -0.27
    ❋
    -0.24
    msgSender
    -0.24
    POSITIVE LOGITS
    [@BOS@]
    0.77
    <unused8>
    0.76
    <unused41>
    0.76
    <unused52>
    0.76
    <unused14>
    0.76
    <unused17>
    0.76
    <unused43>
    0.76
    <unused79>
    0.76
    <unused74>
    0.76
    <pad>
    0.75
    Act Density 0.258%

    No Known Activations