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

    Neuronpedia

    INDEX
    Explanations

    _read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     la
    -0.06
     Patt
    -0.06
     **↵
    -0.06
    [*
    -0.06
    ưng
    -0.06
    摆
    -0.06
     suyu
    -0.06
    _TI
    -0.06
    르
    -0.06
     Naming
    -0.06
    POSITIVE LOGITS
     محافظ
    0.07
    rical
    0.07
     руч
    0.07
     марш
    0.07
    Э
    0.07
     режим
    0.06
     инт
    0.06
     kromě
    0.06
     ngăn
    0.06
    ูน
    0.06
    Act Density 0.173%

    No Known Activations