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

    Neuronpedia

    INDEX
    Explanations

    percentages and keyword density

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وس
    -0.07
     Cruz
    -0.07
     alegr
    -0.07
    DU
    -0.07
    们
    -0.07
    Additionally
    -0.07
    astian
    -0.07
     Bent
    -0.07
    AST
    -0.07
     resultant
    -0.07
    POSITIVE LOGITS
     счита
    0.09
     lymph
    0.09
     மே
    0.08
    葡
    0.08
     она
    0.08
     葡
    0.08
     Miss
    0.08
     mire
    0.08
     показатель
    0.08
     карта
    0.08
    Act Density 0.007%

    No Known Activations