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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yok
    -0.08
     embedded
    -0.07
     mellom
    -0.07
     kone
    -0.07
     MACH
    -0.07
     использование
    -0.07
     EUA
    -0.07
     infographic
    -0.07
     Alonso
    -0.07
     இருப்ப
    -0.07
    POSITIVE LOGITS
    ++;↵↵
    0.09
    ++;↵
    0.08
    ++];↵
    0.08
    ;++
    0.08
     creciente
    0.08
     continuously
    0.08
     crescente
    0.08
    נים
    0.08
    נ
    0.07
    ));↵
    0.07
    Act Density 0.008%

    No Known Activations