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

    Neuronpedia

    INDEX
    Explanations

    occurrences of multi-line string delimiters in programming code

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

    user input and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zoude
    -0.61
     Biôgrafia
    -0.58
    genodigd
    -0.57
     indígen
    -0.57
     miniaturka
    -0.56
     saveiro
    -0.55
    rungsseite
    -0.52
     IBRARY
    -0.52
    AxisAlignment
    -0.52
    ergic
    -0.52
    POSITIVE LOGITS
    """
    2.03
     """
    1.56
    """
    1.52
    ."""
    1.23
     """
    1.22
    ("""
    1.16
    '''
    1.16
    """"
    1.05
    '''
    1.00
     '''
    0.94
    Act Density 0.002%

    No Known Activations