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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oppervlak
    -0.09
     réjou
    -0.09
     �
    -0.08
     Alps
    -0.08
     asio
    -0.08
    ‰
    -0.08
    ुङ
    -0.08
     joys
    -0.08
     alpine
    -0.08
    山县
    -0.08
    POSITIVE LOGITS
     onwards
    0.09
     onward
    0.08
     GT
    0.08
     предложение
    0.08
     Guangzhou
    0.08
    _len
    0.08
    वाही
    0.08
     ситуацию
    0.07
    -ending
    0.07
     下一
    0.07
    Act Density 0.033%

    No Known Activations