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

    Neuronpedia

    INDEX
    Explanations

    Email exchanges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    斯特
    -0.06
     cq
    -0.06
    Proto
    -0.06
    งช
    -0.06
    陸
    -0.06
    esktop
    -0.06
    ibaba
    -0.06
    OU
    -0.06
    FN
    -0.06
    anmar
    -0.06
    POSITIVE LOGITS
    >()↵↵
    0.07
    eltas
    0.07
     السكان
    0.06
    mesinin
    0.06
     permanent
    0.06
    Giving
    0.06
     buys
    0.06
     трансп
    0.06
     Paran
    0.06
    .setState
    0.06
    Act Density 0.016%

    No Known Activations