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

    Neuronpedia

    INDEX
    Explanations

    effort

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	vertices
    -0.07
    的时代
    -0.07
    egov
    -0.07
    markets
    -0.07
     different
    -0.06
    .General
    -0.06
    Declaration
    -0.06
     gearbox
    -0.06
     advantages
    -0.06
    Dash
    -0.06
    POSITIVE LOGITS
     dining
    0.08
    'e
    0.07
    OTION
    0.07
     ly
    0.07
    兹
    0.07
    леп
    0.07
    .TextField
    0.07
    'i
    0.07
    collections
    0.07
    ²
    0.07
    Act Density 0.011%

    No Known Activations