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

    Neuronpedia

    INDEX
    Explanations

    dining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    就会
    -0.07
     riders
    -0.07
     descend
    -0.06
     уменьш
    -0.06
     درجة
    -0.06
    컵
    -0.06
    ultimate
    -0.06
    โลย
    -0.06
    CURRENT
    -0.06
    들을
    -0.06
    POSITIVE LOGITS
    _DIR
    0.07
     imag
    0.07
     courtroom
    0.07
     Hampton
    0.07
    Reject
    0.06
     Walnut
    0.06
    .С
    0.06
     empathy
    0.06
    unable
    0.06
    .BufferedReader
    0.06
    Act Density 0.002%

    No Known Activations