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

    Neuronpedia

    INDEX
    Explanations

    province

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     financ
    -0.07
     kå
    -0.07
    يرا
    -0.07
     cet
    -0.07
     Cain
    -0.07
    Civil
    -0.06
     legalized
    -0.06
    алась
    -0.06
     bitterly
    -0.06
     grou
    -0.06
    POSITIVE LOGITS
    \"><
    0.06
    ]("
    0.06
     CD
    0.06
     PAC
    0.06
    ("__
    0.06
     slož
    0.06
     대상
    0.06
     都
    0.06
     прост
    0.06
    ίναι
    0.06
    Act Density 0.008%

    No Known Activations