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

    Neuronpedia

    INDEX
    Explanations

    listing examples and etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trei
    0.32
     drei
    0.32
     três
    0.31
     trois
    0.28
    nome
    0.28
     antaranya
    0.28
    ３
    0.28
     wọn
    0.27
     തുറ
    0.26
     three
    0.26
    POSITIVE LOGITS
     등이
    0.56
     ইত্যাদি
    0.54
    など
    0.54
    などの
    0.53
    なども
    0.53
     etc
    0.52
    などが
    0.51
    等等
    0.50
    などは
    0.50
     тощо
    0.50
    Act Density 0.387%

    No Known Activations