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

    Neuronpedia

    INDEX
    Explanations

    testing and assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hanem
    0.46
     totalling
    0.40
     anda
    0.39
    致します
    0.39
     налого
    0.39
    kap
    0.39
    iali
    0.39
    ائق
    0.39
    primir
    0.38
     biais
    0.38
    POSITIVE LOGITS
    类
    0.48
    Ox
    0.45
    রি
    0.43
     conventional
    0.43
    鰓
    0.43
     cease
    0.42
     young
    0.41
    docker
    0.41
    ዐ
    0.41
    ಕ್‌
    0.41
    Act Density 0.001%

    No Known Activations