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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soothing
    -0.06
    wr
    -0.06
    olatile
    -0.06
    確
    -0.06
    53
    -0.06
     한국
    -0.06
     Pg
    -0.05
     yöntem
    -0.05
     pronounced
    -0.05
    ยา
    -0.05
    POSITIVE LOGITS
    '>
↵
    0.08
     Allies
    0.07
    那么
    0.07
    وط
    0.07
    =mysql
    0.07
    TEX
    0.07
    (frame
    0.07
    .conn
    0.06
    (out
    0.06
     NBA
    0.06
    Act Density 0.008%

    No Known Activations