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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     excuses
    -0.07
    ريف
    -0.06
    سازی
    -0.06
     sh
    -0.06
     shiny
    -0.06
    ımlar
    -0.06
     spectral
    -0.06
    	width
    -0.05
     mee
    -0.05
     confidence
    -0.05
    POSITIVE LOGITS
     Đề
    0.07
     дос
    0.06
     authToken
    0.06
    Rpc
    0.06
    alta
    0.06
     облад
    0.06
     Auss
    0.06
    dings
    0.06
     댓글
    0.06
     jue
    0.06
    Act Density 0.000%

    No Known Activations