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

    Neuronpedia

    INDEX
    Explanations

    25

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (descriptor
    -0.07
     класс
    -0.07
     JSONObject
    -0.07
    iolet
    -0.07
    _override
    -0.06
     Ballet
    -0.06
     cùng
    -0.06
     şek
    -0.06
     presum
    -0.06
    jà
    -0.06
    POSITIVE LOGITS
    25
    0.10
    025
    0.09
    MV
    0.08
    ۲۵
    0.07
    with
    0.07
    250
    0.07
     Rick
    0.07
    vine
    0.07
    625
    0.07
    received
    0.06
    Act Density 0.042%

    No Known Activations