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

    Neuronpedia

    INDEX
    Explanations

    comparing categories or values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     партне
    0.48
     جيڪ
    0.46
     symptômes
    0.45
     ferrugine
    0.44
     ಸಮಸ್ಯ
    0.44
     کوډ
    0.44
     הם
    0.44
     nombreuses
    0.43
    انہوں
    0.43
     collegamento
    0.43
    POSITIVE LOGITS
    Compare
    0.88
     Comparisons
    0.87
     Comparison
    0.84
     comparison
    0.82
    Comparing
    0.82
     compare
    0.81
    Comparison
    0.81
     срав
    0.80
     COMPAR
    0.80
     Compare
    0.80
    Act Density 0.005%

    No Known Activations