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

    Neuronpedia

    INDEX
    Explanations

    x, r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,↵↵↵
    -0.08
     സമൂഹ
    -0.08
     लेने
    -0.08
    _numpy
    -0.07
    (↵↵
    -0.07
     surprises
    -0.07
    utsche
    -0.07
     Fram
    -0.07
    ={`/
    -0.07
    ,set
    -0.07
    POSITIVE LOGITS
     derived
    0.08
     Aside
    0.08
    Aside
    0.08
     bağlı
    0.07
     cheating
    0.07
     WY
    0.07
     besides
    0.07
    ậy
    0.07
    除了
    0.07
     aside
    0.07
    Act Density 0.016%

    No Known Activations