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

    Neuronpedia

    INDEX
    Explanations

    programming syntax or symbols often used in coding contexts

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

    function calls with matching parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.82
     kasarigan
    -0.65
     Roskov
    -0.63
     ujednoznacz
    -0.61
    DockStyle
    -0.58
    SequentialGroup
    -0.58
     JpaRepository
    -0.56
    oredCriteria
    -0.55
    SBATCH
    -0.55
     suivantes
    -0.54
    POSITIVE LOGITS
    ↵↵↵
    0.54
    ↵↵↵↵
    0.42
    (
    0.41
     (
    0.40
    <eos>
    0.40
    ↵
    0.39
    RegressionTest
    0.38
    ↵↵
    0.37
     
    0.36
    ide
    0.36
    Act Density 0.006%

    No Known Activations