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

    Neuronpedia

    INDEX
    Explanations

    legal terms related to software licensing

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

    Text after headings/descriptions

    np_acts-logits-general · gemini-2.0-flash

    context description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    j
    -0.65
    <eos>
    -0.60
     i
    -0.54
    ↵
    -0.50
    J
    -0.49
     
    -0.49
     x
    -0.48
     d
    -0.48
    ↵↵
    -0.48
     +
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    1.22
     ExecuteAsync
    1.16
    BibitemShut
    1.08
     مشين
    1.03
     itſelf
    1.02
    .";
    0.99
    NUMX
    0.97
    ſelf
    0.96
    neſs
    0.96
    Datuak
    0.95
    Act Density 0.048%

    No Known Activations