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

    Neuronpedia

    INDEX
    Explanations

    to followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிருந்தால்
    0.46
    κή
    0.43
     suffisamment
    0.43
     ри
    0.42
     জাতিসংঘ
    0.42
    ◘
    0.42
     années
    0.41
     lua
    0.41
    ched
    0.40
     bordered
    0.39
    POSITIVE LOGITS
    र
    0.64
    or
    0.52
    varying
    0.52
    臾
    0.52
     tanto
    0.49
    юць
    0.46
    arele
    0.46
    ご確認ください
    0.45
    covery
    0.45
     maximise
    0.45
    Act Density 0.293%

    No Known Activations