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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical tests and distributions

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

    testing math operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.45
     itſelf
    -0.40
    期刊论文
    -0.40
    Архівовано
    -0.38
    ึ้น
    -0.35
    principalTable
    -0.35
    istoitu
    -0.35
     CHtml
    -0.35
    addPreferredGap
    -0.33
     Inscrivez
    -0.33
    POSITIVE LOGITS
    proofing
    0.59
    RegressionTest
    0.58
     TESTING
    0.57
     verifies
    0.57
    Prueba
    0.56
     verifying
    0.56
     testing
    0.56
    EndInit
    0.55
    Testing
    0.54
    Verify
    0.54
    Act Density 0.034%

    No Known Activations