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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     возникает
    -0.09
     возник
    -0.08
     ontstaan
    -0.08
     Pyr
    -0.08
    .xaml
    -0.08
    파
    -0.08
    缩
    -0.08
     sửa
    -0.07
    ώς
    -0.07
     승
    -0.07
    POSITIVE LOGITS
     secrets
    0.09
    recommended
    0.09
     توص
    0.09
     horrible
    0.09
     benign
    0.09
     recomand
    0.09
     straat
    0.09
    computed
    0.08
     secr
    0.08
     autogenerated
    0.08
    Act Density 0.002%

    No Known Activations