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

    Neuronpedia

    INDEX
    Explanations

    legal and financial agreements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lên
    -0.07
    cao
    -0.07
     людина
    -0.07
    ening
    -0.06
    marks
    -0.06
    represented
    -0.06
    else
    -0.06
     mesmo
    -0.06
    acking
    -0.06
    ivní
    -0.06
    POSITIVE LOGITS
    Automatic
    0.07
    ']).
    0.06
    ฤษ
    0.06
     choking
    0.06
     정확
    0.06
     halftime
    0.06
    	resp
    0.06
    charg
    0.06
    _listener
    0.06
    Inventory
    0.06
    Act Density 0.018%

    No Known Activations