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

    Neuronpedia

    INDEX
    Explanations

    elements related to data structures or formatting in programming, particularly associated with JSON-like syntax

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

    region identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.81
    endregion
    -0.71
    ⟬
    -0.68
    featureID
    -0.65
     $_(
    -0.63
    IUrlHelper
    -0.59
     betweenstory
    -0.59
    <unused28>
    -0.58
    <unused8>
    -0.58
    <unused1>
    -0.58
    POSITIVE LOGITS
     œufs
    0.34
     remercier
    0.34
     nomme
    0.34
     Belanda
    0.33
    itní
    0.32
     esprits
    0.32
    ReactDOM
    0.31
     الرياضيه
    0.30
     missão
    0.30
     fysis
    0.30
    Act Density 0.074%

    No Known Activations