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

    Neuronpedia

    INDEX
    Explanations

    relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tqdm
    -0.07
     TEN
    -0.07
     Volley
    -0.07
    릎
    -0.07
    Cmd
    -0.07
    .controllers
    -0.07
     plot
    -0.06
     caffe
    -0.06
     Train
    -0.06
     four
    -0.06
    POSITIVE LOGITS
     مست
    0.09
    _methods
    0.08
    众所周
    0.07
     rút
    0.07
     benefits
    0.07
    	constructor
    0.07
     Arabs
    0.07
    深知
    0.07
     portals
    0.06
     nhập
    0.06
    Act Density 0.005%

    No Known Activations