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

    Neuronpedia

    INDEX
    Explanations

    listing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ऐसा
    0.85
     этом
    0.83
     этим
    0.83
     этого
    0.81
     многих
    0.78
     بهذه
    0.78
     زیادی
    0.77
     tohoto
    0.75
     অনেক
    0.75
     இதை
    0.73
    POSITIVE LOGITS
     discussions
    1.41
     concerns
    1.40
     attempts
    1.40
     questions
    1.34
     efforts
    1.29
     suggestions
    1.28
     explorations
    1.28
     considerations
    1.27
     descriptions
    1.18
     issues
    1.18
    Act Density 0.160%

    No Known Activations