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

    Neuronpedia

    INDEX
    Explanations

    software commands and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     biops
    0.41
    而在
    0.39
    rasse
    0.39
    دا
    0.37
    getPath
    0.37
    極
    0.37
    ার্ভ
    0.36
    結局
    0.36
    alles
    0.36
     steaks
    0.36
    POSITIVE LOGITS
     використання
    0.44
     мати
    0.43
     Kubernetes
    0.43
     മറ്റ്
    0.41
    0.40
     mehreren
    0.39
    深圳市
    0.39
     Eduardo
    0.39
    ~$
    0.39
     викона
    0.39
    Act Density 0.000%

    No Known Activations