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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    …”
    0.61
    그
    0.61
    rrbracket
    0.59
     provoked
    0.53
     engender
    0.53
    ၎င်း
    0.53
    쨰
    0.52
    à
    0.52
    À
    0.52
    \...
    0.51
    POSITIVE LOGITS
    ="
    0.73
     altres
    0.69
     otros
    0.69
     lainnya
    0.69
     aantal
    0.68
    的其他
    0.67
    ("
    0.67
     outras
    0.66
     tipo
    0.66
    อื่นๆ
    0.66
    Act Density 0.337%

    No Known Activations