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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     featuring
    -0.08
     language
    -0.07
    istine
    -0.06
     Jerry
    -0.06
     province
    -0.06
     Streaming
    -0.06
     gens
    -0.06
    мена
    -0.06
     tty
    -0.06
     Language
    -0.06
    POSITIVE LOGITS
    	mesh
    0.06
     Jessie
    0.06
    оф
    0.06
     harsh
    0.06
    有效
    0.06
     adept
    0.06
     mies
    0.06
    DIRECT
    0.06
    olon
    0.06
    áln
    0.06
    Act Density 0.005%

    No Known Activations