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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ítear
    -0.09
     сотрудники
    -0.08
     carbur
    -0.08
    工作人员
    -0.08
    ún
    -0.08
     ezek
    -0.08
    íonn
    -0.08
    uga
    -0.07
     функция
    -0.07
     सेना
    -0.07
    POSITIVE LOGITS
     prive
    0.07
     מחדש
    0.07
     differently
    0.07
     kas
    0.07
     lik
    0.07
    后的
    0.07
     outsourcing
    0.07
     venture
    0.07
     Diane
    0.07
    ları
    0.07
    Act Density 0.026%

    No Known Activations