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

    Neuronpedia

    INDEX
    Explanations

    actor names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    зок
    0.59
    ংলার
    0.56
     ছিলোনা
    0.55
     pavatt
    0.54
    ဈ
    0.54
     एप्प
    0.53
    ಲ್ಯಾ
    0.53
    books
    0.53
    Blogs
    0.53
     sabbam
    0.52
    POSITIVE LOGITS
     her
    0.67
    </h2>
    0.66
     as
    0.61
     به
    0.61
     aan
    0.59
     were
    0.59
    ").
    0.57
     بم
    0.57
     zu
    0.57
    "),
    0.56
    Act Density 0.005%

    No Known Activations