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

    Neuronpedia

    INDEX
    Explanations

    questions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lox
    0.92
    ucho
    0.90
     лишь
    0.90
     millions
    0.88
    axter
    0.88
     vast
    0.88
     billions
    0.86
     countless
    0.85
     many
    0.84
     few
    0.83
    POSITIVE LOGITS
    或者
    1.87
    或其他
    1.77
    或者是
    1.64
    หรือ
    1.62
     atau
    1.61
     bzw
    1.61
     அல்லது
    1.61
     veya
    1.61
     nebo
    1.60
    ／
    1.59
    Act Density 0.732%

    No Known Activations