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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ھە
    -0.09
     حاج
    -0.08
     ilikuwa
    -0.08
    лаа
    -0.08
     मिली
    -0.08
     башҡ
    -0.08
     Ç
    -0.08
     Դա
    -0.08
     bonheur
    -0.07
     frightened
    -0.07
    POSITIVE LOGITS
     Accordingly
    0.08
    ujte
    0.07
     Surveys
    0.07
    ধ
    0.07
    方式
    0.07
     Minim
    0.07
     Sto
    0.07
    BST
    0.07
     Gains
    0.07
     clusters
    0.07
    Act Density 0.135%

    No Known Activations