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

    Neuronpedia

    INDEX
    Explanations

    xy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	col
    -0.07
    .ul
    -0.07
     healed
    -0.07
    Wil
    -0.07
    Jul
    -0.07
    'na
    -0.07
    ↵	↵
    -0.07
     peel
    -0.07
     pagination
    -0.07
    ,',
    -0.07
    POSITIVE LOGITS
     oxy
    0.11
    oxy
    0.11
    xy
    0.10
    y
    0.09
    py
    0.09
     Garcia
    0.08
    Y
    0.08
    zy
    0.08
    XY
    0.07
    ousy
    0.07
    Act Density 0.010%

    No Known Activations