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

    Neuronpedia

    INDEX
    Explanations

    relationships and interactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carav
    -0.08
    ведение
    -0.07
     introductions
    -0.07
     trei
    -0.07
     awal
    -0.07
    Disconnected
    -0.07
    OME
    -0.07
    -0.07
     تتح
    -0.07
    Function
    -0.07
    POSITIVE LOGITS
     zároveň
    0.09
    meter
    0.08
     Hola
    0.08
     eigenlijk
    0.08
     samtidig
    0.07
     법
    0.07
    ­s
    0.07
     Linux
    0.07
     proc
    0.07
     multiples
    0.07
    Act Density 0.106%
    No Known Activations