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

    Neuronpedia

    INDEX
    Explanations

    multilingual explanations with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ძალიან
    0.78
     ഉള്ള
    0.77
     kanske
    0.73
    វែង
    0.73
     என்ன
    0.72
    害怕
    0.72
     trochę
    0.72
     اقول
    0.71
     ছিলোনা
    0.71
     থাকিলে
    0.71
    POSITIVE LOGITS
    。
    0.87
    ).
    0.86
    ¹.
    0.82
     (
    0.78
    ,
    0.77
    <sup>
    0.74
    .
    0.74
     [(
    0.73
    であり
    0.71
    ².
    0.70
    Act Density 0.003%

    No Known Activations