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

    Neuronpedia

    INDEX
    Explanations

    specific types of code syntax or block terminators in programming

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

    code test assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.74
     Efq
    -0.69
     للاسماء
    -0.64
    fromnode
    -0.60
     ſon
    -0.60
    MemoryWarning
    -0.59
     témoig
    -0.59
     ſta
    -0.58
     ſont
    -0.58
    ſelf
    -0.58
    POSITIVE LOGITS
    assertEquals
    0.47
    assertEqual
    0.41
     tegens
    0.40
    assertFalse
    0.37
     result
    0.36
    XCTAssertEqual
    0.36
    verifyException
    0.36
     indeed
    0.35
     pesar
    0.35
     despite
    0.34
    Act Density 0.016%

    No Known Activations