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

    Neuronpedia

    INDEX
    Explanations

    request for comment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Visualization
    -0.08
    Menu
    -0.08
    ,s
    -0.07
    Theme
    -0.07
    Method
    -0.07
    -menu
    -0.07
     Lang
    -0.07
    皇
    -0.07
    ovs
    -0.07
     oth
    -0.07
    POSITIVE LOGITS
     wpły
    0.09
     knowledgeable
    0.08
     sworn
    0.08
     વિન
    0.08
     journée
    0.08
     insinu
    0.08
     દિવસ
    0.08
     tac
    0.08
     хугаца
    0.08
     trenta
    0.08
    Act Density 0.036%

    No Known Activations