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

    Neuronpedia

    INDEX
    Explanations

    mother

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    두
    -0.07
     HG
    -0.07
     UIP
    -0.07
    CDC
    -0.07
    Outdoor
    -0.06
     royal
    -0.06
     onload
    -0.06
     academia
    -0.06
     vlak
    -0.06
     G
    -0.06
    POSITIVE LOGITS
    ]]);↵
    0.07
    )]);↵
    0.06
    ']).
    0.06
     diyor
    0.06
    !;↵
    0.06
    )).
    0.06
    ]].
    0.06
    ))).
    0.06
     fint
    0.06
    ());↵↵↵
    0.05
    Act Density 0.004%

    No Known Activations