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

    Neuronpedia

    INDEX
    Explanations

    dive into podcast topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     것은
    0.56
     эта
    0.55
     subter
    0.54
    जन्
    0.53
     выращи
    0.53
     வழங்கப்படும்
    0.52
     Eta
    0.52
     dioxide
    0.51
    αλλ
    0.51
    ámenes
    0.51
    POSITIVE LOGITS
    Podcast
    0.83
     podcast
    0.70
    podcast
    0.68
     Podcast
    0.66
     podcasts
    0.66
    track
    0.55
    คับ
    0.54
    Co
    0.52
    ्रे
    0.51
    พี่
    0.51
    Act Density 0.008%

    No Known Activations