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

    Neuronpedia

    INDEX
    Explanations

    than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และการ
    0.39
     সংজ্ঞা
    0.38
    只会
    0.38
     शुल्क
    0.37
    如果是
    0.37
     tao
    0.37
     transición
    0.37
     осві
    0.36
     হইলেই
    0.36
     næ
    0.36
    POSITIVE LOGITS
    Than
    0.50
    than
    0.49
    Ante
    0.47
     than
    0.44
     decât
    0.39
     ніж
    0.39
    UTE
    0.39
    úrese
    0.38
     niż
    0.38
     Ante
    0.37
    Act Density 0.005%

    No Known Activations