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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Police
    -0.08
    Te
    -0.08
     Polisi
    -0.07
     doubles
    -0.07
     bolo
    -0.07
    -double
    -0.07
    化
    -0.07
     hospitalization
    -0.07
    Hall
    -0.07
     Te
    -0.07
    POSITIVE LOGITS
     Zweck
    0.08
     উদ্দেশ
    0.08
     fəaliyyət
    0.08
     legends
    0.08
     zonse
    0.08
     faol
    0.08
    _signup
    0.07
     outlines
    0.07
     उद्देश्य
    0.07
    ា
    0.07
    Act Density 0.027%

    No Known Activations