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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lowest
    -0.07
     PK
    -0.07
    Trou
    -0.06
    vertical
    -0.06
    prov
    -0.06
    خط
    -0.06
     рек
    -0.06
    .space
    -0.06
     fran
    -0.06
     colon
    -0.06
    POSITIVE LOGITS
    \Tests
    0.06
     Pedido
    0.06
     nimi
    0.06
    /meta
    0.06
    +'&
    0.06
    стро
    0.06
    ergisi
    0.06
     Ludwig
    0.06
    makt
    0.06
     غذ
    0.06
    Act Density 0.008%

    No Known Activations