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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dık
    -0.08
    .want
    -0.07
    깆
    -0.07
     dared
    -0.07
    要做
    -0.07
    =\"%
    -0.07
    dana
    -0.07
    _INDEX
    -0.07
    傩
    -0.07
    !")
↵
    -0.07
    POSITIVE LOGITS
    (::
    0.07
    Gro
    0.07
     postcode
    0.07
    产品的
    0.07
    III
    0.07
     Pri
    0.07
    ATTER
    0.07
     hull
    0.07
    (Media
    0.07
    Chelsea
    0.07
    Act Density 0.003%

    No Known Activations