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

    Neuronpedia

    INDEX
    Explanations

    boilerplate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disadvantaged
    -0.07
    omer
    -0.06
    	result
    -0.06
     Bonnie
    -0.06
     Brexit
    -0.06
    面積
    -0.06
     flotation
    -0.06
     prima
    -0.06
     Lucy
    -0.06
    Gil
    -0.06
    POSITIVE LOGITS
    мах
    0.07
    cek
    0.07
    ()])↵
    0.06
    ağ
    0.06
    imesteps
    0.06
    utterstock
    0.06
    òng
    0.06
    �
    0.06
     toward
    0.06
     ofApp
    0.05
    Act Density 0.000%

    No Known Activations