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

    Neuronpedia

    INDEX
    Explanations

    encoding and character issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CWE
    -0.07
    ेखन
    -0.06
    kuk
    -0.06
    ुक
    -0.06
    Bien
    -0.06
    िब
    -0.06
    )\↵
    -0.06
    cki
    -0.05
     orderId
    -0.05
    ла
    -0.05
    POSITIVE LOGITS
    !</
    0.07
     NEWS
    0.06
    ôt
    0.06
     gate
    0.06
    192
    0.06
    ágenes
    0.06
     совсем
    0.06
    >'.
    0.06
     Frames
    0.06
    .rs
    0.06
    Act Density 0.063%

    No Known Activations