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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of contrasts or exceptions

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

    "Even" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.49
    iettivo
    -0.44
    ItemBackground
    -0.42
    ParallelGroup
    -0.41
    queryInterface
    -0.40
    IActionResult
    -0.40
    urlopen
    -0.40
    DidLoad
    -0.39
    问道
    -0.38
    unehmen
    -0.38
    POSITIVE LOGITS
     sekal
    0.67
    Даже
    0.62
    Even
    0.60
     even
    0.59
     Even
    0.57
    even
    0.56
     Даже
    0.56
    ThroughAttribute
    0.55
     persino
    0.54
    Mesmo
    0.54
    Act Density 0.181%

    No Known Activations