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

    Neuronpedia

    INDEX
    Explanations

    below freezing temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     heat
    0.71
    熱
    0.70
     Heat
    0.69
     हीट
    0.69
     тепло
    0.68
    Heat
    0.66
    热
    0.66
     overheat
    0.66
     нагре
    0.65
     गर्मी
    0.64
    POSITIVE LOGITS
     freezing
    0.80
     below
    0.67
     snowy
    0.66
     zero
    0.65
     frozen
    0.63
     snow
    0.61
     $(-
    0.59
     negative
    0.59
    雪
    0.59
     cold
    0.58
    Act Density 0.027%

    No Known Activations