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

    Neuronpedia

    INDEX
    Explanations

    code-specific syntax and structures, particularly related to conditionals and function definitions

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

    Code assertions, checks, or error handling

    np_acts-logits-general · gemini-2.0-flash

    asserting conditions using if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.62
    所示
    -0.47
     jScrollPane
    -0.47
    bewerken
    -0.46
    ="@+
    -0.45
     sī
    -0.44
    ссмо
    -0.42
    PyObject
    -0.42
    TAKT
    -0.42
    enio
    -0.42
    POSITIVE LOGITS
    assert
    1.35
    Assert
    1.16
    ensure
    1.12
    Preconditions
    1.12
     ensure
    1.11
     ensured
    1.08
    check
    1.06
     checks
    1.03
     check
    1.03
     assert
    1.02
    Act Density 0.191%

    No Known Activations