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

    Neuronpedia

    INDEX
    Explanations

    primality test for loop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பின்பற்ற
    0.42
     भूषण
    0.40
     relinquished
    0.39
    交易
    0.39
    emás
    0.38
     farce
    0.38
     ফারুক
    0.38
     रंजन
    0.37
     বাবুর
    0.37
     निराशा
    0.37
    POSITIVE LOGITS
    terminal
    0.45
     hepat
    0.43
     terminal
    0.39
    apm
    0.39
     inqu
    0.37
    appa
    0.36
     secretario
    0.36
    区
    0.36
     serum
    0.35
     html
    0.35
    Act Density 0.002%

    No Known Activations