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

    Neuronpedia

    INDEX
    Explanations

    negative numbers and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    กิน
    0.52
    Imidazole
    0.52
    मॉडल
    0.52
    കളിൽ
    0.48
    म्यान
    0.48
    ina
    0.47
    این
    0.47
    ighthouse
    0.47
    ם
    0.47
    Historia
    0.47
    POSITIVE LOGITS
     (-)
    0.83
     (-
    0.77
     negative
    0.73
     (−
    0.72
     $(-
    0.68
    (-
    0.63
     отрица
    0.61
     negatives
    0.60
    negative
    0.59
    }=-
    0.59
    Act Density 0.103%

    No Known Activations