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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to health, treatment, and medical conditions

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

    Following nouns (cells, time, debt, etc) with "is" or similar

    np_acts-logits-general · gemini-2.0-flash

    is or constitutes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.78
     uſe
    -0.70
    ]();
    -0.69
    ")));
    -0.65
     Majefty
    -0.65
     myſelf
    -0.64
    RegressionTest
    -0.64
    "):
    -0.64
    FieldBuilder
    -0.64
    :");
    -0.63
    POSITIVE LOGITS
     is
    1.43
     adalah
    1.07
     merupakan
    1.02
     seems
    0.99
     là
    0.99
     constitue
    0.97
     является
    0.94
     constitutes
    0.88
    是最
    0.87
     είναι
    0.87
    Act Density 0.693%

    No Known Activations