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

    Neuronpedia

    INDEX
    Explanations

    another or other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఎవరు
    0.77
     notamment
    0.73
    中最
    0.73
     sekä
    0.72
    이며
    0.72
    celikle
    0.69
     wszel
    0.69
     самых
    0.69
    更是
    0.68
     ludzie
    0.67
    POSITIVE LOGITS
     another
    5.24
    another
    4.83
    Another
    4.68
     Another
    4.54
     otro
    4.39
     otra
    4.36
     другой
    4.26
     outra
    4.19
    另一个
    4.14
     autre
    4.01
    Act Density 1.507%

    No Known Activations