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

    Neuronpedia

    INDEX
    Explanations

    info

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrevistas
    -0.09
     perguntas
    -0.08
     Gespr
    -0.08
    Xs
    -0.08
     chis
    -0.08
     haz
    -0.08
    NESS
    -0.07
    /Card
    -0.07
    -ui
    -0.07
     hydraul
    -0.07
    POSITIVE LOGITS
    基础
    0.08
    ಿದು
    0.08
     mengenai
    0.08
    เกี่ยว
    0.08
    efficient
    0.07
     согласно
    0.07
     Polo
    0.07
     كيفية
    0.07
     về
    0.07
     efficiently
    0.07
    Act Density 0.016%

    No Known Activations