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

    Neuronpedia

    INDEX
    Explanations

    Code/Data Artifacts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .queue
    -0.07
    _translation
    -0.06
     更新
    -0.06
    _bn
    -0.06
    _trampoline
    -0.06
     Bunlar
    -0.06
    ientras
    -0.06
    	parser
    -0.06
     Messi
    -0.06
    (device
    -0.06
    POSITIVE LOGITS
     Von
    0.07
     Never
    0.07
     Wu
    0.07
    腐
    0.07
    Lisa
    0.06
     Derby
    0.06
     комп
    0.06
     Noir
    0.06
     der
    0.06
    	public
    0.06
    Act Density 0.000%

    No Known Activations