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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     פּ
    0.45
     П
    0.42
     भरे
    0.40
     п
    0.38
    ছের
    0.38
    }}}-\
    0.37
    ĥ
    0.37
    ଛି
    0.37
     प
    0.36
    აპ
    0.36
    POSITIVE LOGITS
     Peterson
    0.40
     البيان
    0.40
    webs
    0.39
    iez
    0.39
    ۲۰
    0.39
    express
    0.39
    ಔ
    0.38
     Informatika
    0.38
    ensive
    0.38
    esm
    0.38
    Act Density 0.001%

    No Known Activations