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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brethren
    -0.07
    ीद
    -0.06
     classrooms
    -0.06
     самым
    -0.06
    увала
    -0.06
     barcode
    -0.06
     touchdown
    -0.06
    kyně
    -0.06
     broadcasts
    -0.06
    Debugger
    -0.06
    POSITIVE LOGITS
    �建
    0.07
    Ing
    0.06
    .fromRGBO
    0.06
    uing
    0.06
    за
    0.06
     receives
    0.06
    .assertFalse
    0.06
    .light
    0.06
    гот
    0.06
    _ER
    0.06
    Act Density 0.101%

    No Known Activations