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

    Neuronpedia

    INDEX
    Explanations

    exclamations and interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.65
    ik
    0.57
    i
    0.53
    ఒ
    0.53
    كتب
    0.52
    GJ
    0.52
    क
    0.50
    im
    0.50
    Để
    0.50
    ంబేద్కర్
    0.50
    POSITIVE LOGITS
     comedy
    0.47
     kidding
    0.46
     sailor
    0.46
     admiring
    0.46
     horrors
    0.45
     ktorá
    0.44
     comical
    0.44
     famously
    0.44
    是
    0.44
     wonder
    0.44
    Act Density 0.865%

    No Known Activations