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
    用的
    -0.06
     sucess
    -0.06
    /th
    -0.06
     Trong
    -0.06
    _dependencies
    -0.06
    reek
    -0.06
     Mild
    -0.06
    ीसर
    -0.06
    _family
    -0.06
     následující
    -0.06
    POSITIVE LOGITS
     an
    0.10
     a
    0.09
     An
    0.07
     A
    0.07
     Local
    0.07
    (slot
    0.07
    .dateTime
    0.07
    -store
    0.07
     lessen
    0.06
     someone
    0.06
    Act Density 0.016%

    No Known Activations