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

    Neuronpedia

    INDEX
    Explanations

    particular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     better
    -0.07
     Greater
    -0.07
    .goBack
    -0.06
     Miscellaneous
    -0.06
    ispers
    -0.06
    緊
    -0.06
    .File
    -0.06
     С
    -0.06
    Projected
    -0.06
    andra
    -0.06
    POSITIVE LOGITS
     xmin
    0.07
    جی
    0.07
     smě
    0.07
     stream
    0.06
    colors
    0.06
    	ERROR
    0.06
    Set
    0.06
    Cal
    0.06
                             ↵
    0.06
     Pul
    0.06
    Act Density 0.008%

    No Known Activations