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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act · gemini-2.0-flash

    formal elements related to citations in academic writing.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ategories
    -0.08
    _deck
    -0.07
     LEVEL
    -0.06
     level
    -0.06
     lcd
    -0.06
    stdClass
    -0.06
     deck
    -0.06
    enthal
    -0.06
    Act
    -0.06
     levels
    -0.06
    POSITIVE LOGITS
     Citation
    0.07
    ston
    0.07
     справж
    0.07
     Iterator
    0.07
    σιμοποι
    0.07
     poking
    0.07
     someone
    0.07
     exiting
    0.06
     fusion
    0.06
    _UUID
    0.06
    Act Density 0.003%

    No Known Activations