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

    Neuronpedia

    INDEX
    Explanations

    instructions or assignments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    approve
    -0.06
     seniors
    -0.06
    	contentPane
    -0.06
     laughter
    -0.06
     correctly
    -0.06
    Operators
    -0.05
    (">
    -0.05
    ो।
    -0.05
    statuses
    -0.05
     hat
    -0.05
    POSITIVE LOGITS
    송
    0.08
     viewType
    0.07
    ole
    0.07
     Different
    0.07
    ual
    0.07
     outbreaks
    0.07
    Different
    0.07
    erra
    0.06
    .toString
    0.06
     unravel
    0.06
    Act Density 0.005%

    No Known Activations