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

    Neuronpedia

    INDEX
    Explanations

    Numerical computations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    visi
    -0.08
     disposición
    -0.08
     Venet
    -0.08
     تعد
    -0.07
     bono
    -0.07
     ymp
    -0.07
     добы
    -0.07
    card
    -0.07
     disposto
    -0.07
     учет
    -0.07
    POSITIVE LOGITS
    හි
    0.09
     waarschijnlijk
    0.08
     probably
    0.08
    (features
    0.08
    (batch
    0.08
     Probably
    0.08
    했다
    0.07
    났다
    0.07
     runs
    0.07
    හා
    0.07
    Act Density 0.122%

    No Known Activations