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

    Neuronpedia

    INDEX
    Explanations

    comma followed by which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thôn
    0.34
    ناك
    0.32
    🈵
    0.31
     hatta
    0.31
     menengah
    0.31
    кем
    0.31
     dagegen
    0.30
     شود
    0.30
     منهم
    0.30
     sobretudo
    0.30
    POSITIVE LOGITS
     which
    2.41
    which
    2.36
    ซึ่ง
    1.93
     WHICH
    1.83
     который
    1.77
     которая
    1.70
    Which
    1.68
     lequel
    1.68
     który
    1.66
     Which
    1.65
    Act Density 0.107%

    No Known Activations