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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     হওয়ার
    -0.07
    END
    -0.07
    ֵ
    -0.07
     nh
    -0.07
    fi
    -0.07
    -0.07
     NH
    -0.07
     properly
    -0.07
     unusually
    -0.07
     দ্বিতীয়
    -0.07
    POSITIVE LOGITS
     yine
    0.11
     Again
    0.11
     nuevamente
    0.10
    Again
    0.10
     novamente
    0.10
     опять
    0.10
    again
    0.09
     again
    0.09
     ebenfalls
    0.09
     역시
    0.09
    Act Density 0.038%
    No Known Activations