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

    Neuronpedia

    INDEX
    Explanations

    player who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തിൽ
    0.82
    ڽ
    0.79
    ậy
    0.79
     තිබ
    0.79
    ത്തില്‍
    0.78
    에서는
    0.78
    ದಲ್ಲಿ
    0.77
     যৌগ
    0.77
    ございます
    0.77
    ంలో
    0.76
    POSITIVE LOGITS
     who
    6.92
    who
    6.01
     Who
    5.05
    Who
    4.97
     whom
    4.79
     quien
    4.70
     quienes
    4.27
     whos
    4.09
     whose
    4.06
     quién
    4.05
    Act Density 0.800%

    No Known Activations