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

    Neuronpedia

    INDEX
    Explanations

    relative path imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    있다
    0.79
    amazing
    0.66
    {'
    0.65
    တယ်
    0.64
    righteous
    0.64
    burden
    0.63
     глав
    0.62
     bezoek
    0.62
    yside
    0.61
     misty
    0.61
    POSITIVE LOGITS
     "./
    1.51
     './
    1.42
     `./
    1.17
    ./
    1.02
    "./
    0.95
    .–
    0.94
     ./
    0.94
     '.';
    0.93
    ("./
    0.87
    (`./
    0.86
    Act Density 0.007%

    No Known Activations