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

    Neuronpedia

    INDEX
    Explanations

    code syntax delimiters and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |.|.|
    0.46
    ='/'
    0.43
    ;</
    0.43
    (`/
    0.42
     [{\
    0.41
    ),[
    0.41
     [§
    0.41
    (`./
    0.40
     (‘
    0.40
    |</
    0.40
    POSITIVE LOGITS
     "
    1.32
    ("
    1.27
     "$
    1.10
    ="
    1.05
    "
    0.98
     "_
    0.95
     "(
    0.94
     "@
    0.92
     "¿
    0.91
     "__
    0.90
    Act Density 0.458%

    No Known Activations