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

    Neuronpedia

    INDEX
    Explanations

    now

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cao
    -0.07
    ẳn
    -0.06
     ji
    -0.06
    imbabwe
    -0.06
    色
    -0.06
    ableObject
    -0.06
     질
    -0.06
     nguồn
    -0.06
    NSMutableDictionary
    -0.06
    	if
    -0.05
    POSITIVE LOGITS
    ��
    0.07
    .summary
    0.07
    parameters
    0.06
     delighted
    0.06
     R
    0.06
     debug
    0.06
     auth
    0.06
     plot
    0.06
    logging
    0.06
     Trainer
    0.06
    Act Density 0.274%

    No Known Activations