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
     demokrat
    -0.07
     Diaz
    -0.07
     října
    -0.06
     manžel
    -0.06
    罗
    -0.06
    [from
    -0.06
     эксп
    -0.06
    벽
    -0.06
     згод
    -0.06
     Lebanon
    -0.06
    POSITIVE LOGITS
     audi
    0.07
    si
    0.07
     Katie
    0.07
     (?)
    0.07
    !)
    0.06
    idl
    0.06
     Robin
    0.06
    Nİ
    0.06
    ście
    0.06
    )\<
    0.06
    Act Density 0.001%

    No Known Activations