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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     સાચ
    -0.09
     handing
    -0.08
     योग्य
    -0.08
    属于
    -0.08
     projectile
    -0.08
    ిపోయ
    -0.08
    容易
    -0.08
     nominal
    -0.08
     radioactive
    -0.08
    Ј
    -0.08
    POSITIVE LOGITS
     Kumar
    0.09
     Liu
    0.09
     WHO
    0.08
    习近平
    0.08
     Dimit
    0.08
     Nagar
    0.08
     SCORE
    0.08
     Xu
    0.08
     Friedman
    0.08
     Fus
    0.08
    Act Density 0.014%

    No Known Activations