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

    Neuronpedia

    INDEX
    Explanations

    neural network training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dbl
    -0.07
     Implementation
    -0.07
    箱
    -0.07
    UBLE
    -0.07
    Dani
    -0.07
     случае
    -0.07
    >=
    -0.07
    嘱
    -0.06
    فش
    -0.06
     Drone
    -0.06
    POSITIVE LOGITS
     brid
    0.08
    ्�
    0.07
     propriet
    0.07
    렀
    0.07
    يح
    0.06
    	catch
    0.06
    capt
    0.06
     רבות
    0.06
     leurs
    0.06
    想找
    0.06
    Act Density 0.065%

    No Known Activations