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

    Neuronpedia

    INDEX
    Explanations

    Babel transpilation and transformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getpath
    0.40
     vekt
    0.39
    testGet
    0.37
    OfMonth
    0.37
    赢得
    0.37
    redients
    0.36
    FETCH
    0.36
     sockfd
    0.36
     লাহ
    0.36
     বিস্ফ
    0.36
    POSITIVE LOGITS
     transp
    0.94
     Babel
    0.89
     babel
    0.86
    babel
    0.85
     transforms
    0.80
     trans
    0.80
     transform
    0.79
     Transform
    0.78
     Transforming
    0.78
    Transform
    0.77
    Act Density 0.013%

    No Known Activations