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

    Neuronpedia

    INDEX
    Explanations

    fast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supreme
    -0.07
    しの
    -0.07
     참
    -0.06
     Carm
    -0.06
     参
    -0.06
     merkez
    -0.06
     provinc
    -0.06
    ικη
    -0.06
     receptions
    -0.06
     외국
    -0.06
    POSITIVE LOGITS
     YELLOW
    0.06
     fold
    0.06
     BOT
    0.06
    							↵
    0.06
    167
    0.06
    -output
    0.06
     amongst
    0.06
    (EVENT
    0.06
    FileNotFoundException
    0.06
    _online
    0.06
    Act Density 0.024%

    No Known Activations