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

    Neuronpedia

    INDEX
    Explanations

    references to individuals, especially in the context of legal or formal documents

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

    U.S. or Mr. followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zust
    -0.40
    <h1>
    -0.39
    <eos>
    -0.37
     Rettung
    -0.36
     until
    -0.36
    Gruß
    -0.36
    T
    -0.36
    Способ
    -0.35
     Vgl
    -0.34
    __
    -0.34
    POSITIVE LOGITS
    IUrlHelper
    0.77
     kaarangay
    0.75
    addCriterion
    0.73
     يتيمه
    0.73
    SBATCH
    0.65
    tinyos
    0.65
    endpush
    0.64
    InjectAttribute
    0.64
    RegressionTest
    0.64
    AndEndTag
    0.62
    Act Density 0.118%

    No Known Activations