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

    Neuronpedia

    INDEX
    Explanations

    speech and confessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.52
    IMF
    0.44
    стя
    0.41
     totalitarian
    0.41
     gusta
    0.40
     завжди
    0.40
     bebé
    0.40
    ト
    0.40
    ็อก
    0.40
    頑張
    0.39
    POSITIVE LOGITS
     इतर
    0.46
     其他
    0.43
     enzymes
    0.43
    밖
    0.43
     advisor
    0.42
     Opens
    0.41
     parmesan
    0.40
     oars
    0.40
     other
    0.40
    룻
    0.39
    Act Density 0.013%

    No Known Activations