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

    Neuronpedia

    INDEX
    Explanations

    degrees Celsius

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    assert
    -1.05
    ătă
    -1.03
     of
    -0.96
    ).__
    -0.96
     at
    -0.96
    و
    -0.96
    us
    -0.93
    のだろうか
    -0.93
    size
    -0.93
    えっ
    -0.91
    POSITIVE LOGITS
     temperatures
    1.13
     temperature
    1.05
    ਫ਼
    0.92
    erapa
    0.91
     Fahrenheit
    0.91
     Celsius
    0.90
    /−
    0.89
    PERFECT
    0.89
    Celsius
    0.86
     temperat
    0.85
    Act Density 0.027%

    No Known Activations