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

    Neuronpedia

    INDEX
    Explanations

    assertions and equality checks in code

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

    assertions and checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -1.01
     AttributeSet
    -0.96
     initComponents
    -0.92
    MigrationBuilder
    -0.92
    complexContent
    -0.92
    <pad>
    -0.91
    <unused42>
    -0.91
    <unused14>
    -0.91
    <unused8>
    -0.91
    [@BOS@]
    -0.91
    POSITIVE LOGITS
    XCTAssert
    0.42
     kesin
    0.36
     parezca
    0.35
     garantia
    0.35
     Xunit
    0.34
     necesaria
    0.32
     Tatsache
    0.32
     confiable
    0.31
     verdad
    0.30
     apret
    0.30
    Act Density 0.001%

    No Known Activations