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

    Neuronpedia

    INDEX
    Explanations

    you ask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deberán
    0.51
     będzie
    0.45
     découvert
    0.45
     자주
    0.45
    这将
    0.43
     deberá
    0.42
     scoperta
    0.42
     যাতে
    0.42
     сможет
    0.42
     ควร
    0.42
    POSITIVE LOGITS
     ask
    0.67
     asked
    0.59
     preguntar
    0.55
    问
    0.54
     squint
    0.52
    ask
    0.52
    Ask
    0.52
    問
    0.52
     consider
    0.51
     examined
    0.50
    Act Density 0.008%

    No Known Activations