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

    Neuronpedia

    INDEX
    Explanations

    programming-related elements such as functions and code structure

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

    code snippets and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.78
     ApiException
    -0.73
    iſche
    -0.72
     autorytatywna
    -0.71
     deſſen
    -0.69
    <unused79>
    -0.68
    -0.68
    <unused1>
    -0.68
    <unused8>
    -0.68
    <unused14>
    -0.68
    POSITIVE LOGITS
     становника
    0.28
     same
    0.27
    同样
    0.26
    同樣
    0.25
     conference
    0.25
     stesso
    0.25
     объ
    0.24
    ↵↵
    0.24
    rieden
    0.24
     French
    0.24
    Act Density 0.155%

    No Known Activations