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

    Neuronpedia

    INDEX
    Explanations

    split and divide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.61
     in
    0.59
     to
    0.57
     nhưng
    0.55
    も
    0.54
    को
    0.51
    ও
    0.49
     dịch
    0.48
     घंट
    0.47
    도
    0.46
    POSITIVE LOGITS
     split
    0.47
    at
    0.42
    т
    0.41
     cote
    0.40
    у
    0.40
    "});
    0.39
    ubes
    0.39
    و
    0.39
    ar
    0.38
    olecules
    0.38
    Act Density 0.085%

    No Known Activations