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

    Neuronpedia

    INDEX
    Explanations

    references to classified information and materials

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

    classified information or categorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestRunner
    -0.48
     indicaciones
    -0.46
    ethereum
    -0.45
    RectangleBorder
    -0.44
    OrEqualTo
    -0.42
     autonomía
    -0.42
    terdam
    -0.41
     RestTemplate
    -0.41
    Meaning
    -0.41
    Hara
    -0.40
    POSITIVE LOGITS
     classified
    1.97
     Classified
    1.93
    classified
    1.83
    Classified
    1.74
    CLASSIFIED
    1.31
    lassified
    1.29
     classify
    1.27
     classi
    1.11
     categorized
    1.08
     classed
    1.05
    Act Density 0.007%

    No Known Activations