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

    Neuronpedia

    INDEX
    Explanations

    error occurs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menjalani
    0.42
     Kwan
    0.39
    മാക്കി
    0.38
     campañas
    0.38
    ላቸው
    0.36
    不错的
    0.36
     lồ
    0.36
     বানানো
    0.36
    وفيق
    0.36
    としている
    0.35
    POSITIVE LOGITS
     occur
    3.78
     occurs
    3.70
     occurred
    3.44
    occur
    3.34
     occurring
    3.13
     ocorre
    2.94
     occured
    2.91
     ocor
    2.86
     terjadi
    2.83
     occurrence
    2.80
    Act Density 0.086%

    No Known Activations