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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     איך
    -0.07
    (db
    -0.07
     Highest
    -0.06
    �
    -0.06
    .sparse
    -0.06
    .nav
    -0.06
    面包
    -0.06
     Bloom
    -0.06
    EW
    -0.06
    螺旋
    -0.06
    POSITIVE LOGITS
    יצר
    0.07
    主力
    0.07
    �
    0.06
     careers
    0.06
    Sports
    0.06
    .te
    0.06
     Lage
    0.06
     housing
    0.06
    يرا
    0.06
     hn
    0.06
    Act Density 0.001%

    No Known Activations