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

    Neuronpedia

    INDEX
    Explanations

    comparison operators and numeric conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CCCc
    0.50
     کی۔
    0.46
     плюс
    0.44
    uttaa
    0.43
    *;
    0.43
    /;
    0.43
    ஔ
    0.42
    ச்சின்ன
    0.42
    মায়
    0.42
     അതിനാ
    0.42
    POSITIVE LOGITS
     ==
    1.27
     >
    1.25
     >=
    1.25
     !=
    1.19
     <=
    1.13
    ==
    1.03
    >=
    1.02
    !=
    0.95
     ≤
    0.88
    <=
    0.83
    Act Density 0.071%

    No Known Activations