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

    Neuronpedia

    INDEX
    Explanations

    accented characters and language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     d
    0.92
    d
    0.91
     at
    0.88
    تس
    0.79
    dependencies
    0.78
     बड़े
    0.75
     powied
    0.74
     सैकड़ों
    0.74
    o
    0.73
     from
    0.72
    POSITIVE LOGITS
    AR
    0.93
    о
    0.93
    у
    0.92
    й
    0.91
    в
    0.90
    ON
    0.89
    :
    0.89
    та
    0.88
    с
    0.87
    ี
    0.83
    Act Density 0.001%

    No Known Activations