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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sheep
    -0.06
     sheep
    -0.06
     GOP
    -0.06
     muted
    -0.06
     genre
    -0.06
     disturbed
    -0.06
     Scho
    -0.06
     catchy
    -0.06
     CONSTANTS
    -0.06
    ycop
    -0.06
    POSITIVE LOGITS
    Round
    0.08
    	report
    0.07
     inflammation
    0.07
    total
    0.07
     Round
    0.07
    .registry
    0.07
    *S
    0.07
    vekili
    0.07
    のお
    0.06
    ardown
    0.06
    Act Density 0.055%

    No Known Activations