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

    Neuronpedia

    INDEX
    Explanations

    function declaration statements and their expected outputs

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

    Assertions following "should"

    np_acts-logits-general · gemini-2.0-flash

    properly closing correctly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    this
    -0.49
    在此
    -0.46
     here
    -0.44
     Perhaps
    -0.44
     perhaps
    -0.44
    <eos>
    -0.44
     this
    -0.43
    memoized
    -0.43
     destinés
    -0.42
    baka
    -0.41
    POSITIVE LOGITS
     correctly
    1.00
     AssemblyTitle
    0.92
    correctly
    0.91
    properly
    0.84
    rungsseite
    0.82
     properly
    0.82
    RegressionTest
    0.78
     Properly
    0.76
     correct
    0.76
     incorrect
    0.74
    Act Density 0.231%

    No Known Activations