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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    튱
    -0.08
     amendments
    -0.07
    一番
    -0.07
     nouns
    -0.06
    .getRequestDispatcher
    -0.06
    PB
    -0.06
    踒
    -0.06
     Meal
    -0.06
     Nate
    -0.06
    מורים
    -0.06
    POSITIVE LOGITS
    	y
    0.07
    拱
    0.07
     inev
    0.07
     evidence
    0.07
    回到
    0.07
    不可或
    0.07
    acad
    0.07
     guarding
    0.07
     לגרום
    0.06
    geries
    0.06
    Act Density 0.001%

    No Known Activations