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

    Neuronpedia

    INDEX
    Explanations

    instances of structured data or object-oriented programming constructs

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

    Code snippets containing "literal"

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inander
    -0.69
     CreateTagHelper
    -0.64
    Rohy
    -0.59
    lové
    -0.57
    Хьажоргаш
    -0.52
    зулта
    -0.50
    rasil
    -0.49
    ">//
    -0.47
    λων
    -0.46
    MigrationBuilder
    -0.46
    POSITIVE LOGITS
    ]--;
    0.58
    extAlignment
    0.55
     Wikipédia
    0.51
     Normdatei
    0.50
    couvrez
    0.49
    '},
    0.49
    PhysRev
    0.48
     diabe
    0.48
    guenos
    0.47
    workbench
    0.47
    Act Density 0.129%

    No Known Activations