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

    Neuronpedia

    INDEX
    Explanations

    AS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourced
    -0.07
    ソン
    -0.06
     Benson
    -0.06
     Webb
    -0.06
    增长
    -0.06
     McCain
    -0.06
    ểm
    -0.06
    هد
    -0.06
    дат
    -0.06
     đạo
    -0.06
    POSITIVE LOGITS
     bulky
    0.07
     Krishna
    0.07
    June
    0.07
     математи
    0.07
     recognize
    0.07
     """↵
    0.07
    <X
    0.07
     ur
    0.06
     "$
    0.06
    OPSIS
    0.06
    Act Density 0.001%

    No Known Activations