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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and phrases related to function declarations and test assertions

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

    Opening parentheses followed by "should"

    np_acts-logits-general · gemini-2.0-flash

    'should' in test descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     destinés
    -0.54
    hichever
    -0.52
     Wherever
    -0.51
    arschijnlijk
    -0.50
    Wherever
    -0.50
     henceforth
    -0.48
    this
    -0.47
    ImageContext
    -0.47
     wherever
    -0.47
    memoized
    -0.46
    POSITIVE LOGITS
     correctly
    0.99
     properly
    0.87
     when
    0.81
    correctly
    0.80
    properly
    0.80
     AssemblyTitle
    0.77
     correct
    0.77
    rungsseite
    0.76
     Properly
    0.74
     proper
    0.73
    Act Density 0.253%

    No Known Activations