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

    Neuronpedia

    INDEX
    Explanations

    equality and inequality operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    эн
    0.44
    Lloyd
    0.43
    IDOS
    0.42
    Neuro
    0.41
    ÈRE
    0.41
    пети
    0.40
    𝖾
    0.40
    Newman
    0.40
    myTransform
    0.39
    闼
    0.39
    POSITIVE LOGITS
     ==
    0.63
     !=
    0.54
     pytest
    0.50
    ̸
    0.50
    0.49
     equality
    0.47
     d
    0.46
     '-':
    0.46
     "":
    0.46
     ⿻
    0.44
    Act Density 0.037%

    No Known Activations