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

    Neuronpedia

    INDEX
    Explanations

    terms related to data evaluation and testing protocols in machine learning

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

    "train" and "test" datasets

    np_acts-logits-general · gemini-2.0-flash

    train/test/validation splits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.41
     незавершена
    -0.38
     IconData
    -0.36
     répondu
    -0.35
    stdint
    -0.35
    équi
    -0.35
    COUVER
    -0.34
     atención
    -0.34
    ResponseEntity
    -0.34
    🎳
    -0.34
    POSITIVE LOGITS
     חיצוניים
    0.54
    ionario
    0.50
     ModelExpression
    0.49
     Extern
    0.47
     randomly
    0.47
     CART
    0.47
     conting
    0.45
     Halter
    0.45
    initely
    0.45
     Derived
    0.44
    Act Density 0.262%

    No Known Activations