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

    Neuronpedia

    INDEX
    Explanations

    45

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (scale
    -0.07
     HERE
    -0.07
     ليس
    -0.06
     robotics
    -0.06
    _help
    -0.06
     max
    -0.06
    PropertyParams
    -0.06
    _cipher
    -0.06
    —is
    -0.06
     раск
    -0.06
    POSITIVE LOGITS
    rk
    0.08
    ární
    0.07
    การเล
    0.07
    -
    0.06
    оюз
    0.06
    ˆ
    0.06
     #(
    0.06
    Flat
    0.06
     дли
    0.06
    )$
    0.06
    Act Density 0.002%

    No Known Activations