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

    Neuronpedia

    INDEX
    Explanations

    hypotheses and their validation in research contexts

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

    expect finding errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vœ
    -0.37
     garnet
    -0.36
    Ingredienti
    -0.36
     AssemblyTitle
    -0.35
     demain
    -0.35
    }`).
    -0.34
    Specifier
    -0.33
     Lumb
    -0.33
     useContext
    -0.32
    Morocco
    -0.32
    POSITIVE LOGITS
     XCTest
    0.59
     expected
    0.55
     Expect
    0.54
    elemField
    0.54
     expects
    0.52
    новниш
    0.52
     EconPapers
    0.52
     expect
    0.51
    verifyException
    0.49
    ConstraintMaker
    0.49
    Act Density 0.192%

    No Known Activations