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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    降雨
    -0.07
     duo
    -0.07
    Colors
    -0.07
     Tur
    -0.07
     enthusiasts
    -0.06
    当我
    -0.06
    ++++
    -0.06
     doe
    -0.06
    Reporter
    -0.06
    ylv
    -0.06
    POSITIVE LOGITS
    ᠲ
    0.08
    会对
    0.07
     amps
    0.07
    ᛙ
    0.07
    可怕
    0.07
    рак
    0.07
    骒
    0.07
    就近
    0.06
     opposes
    0.06
    event
    0.06
    Act Density 0.002%

    No Known Activations