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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     almost
    -0.07
    /utility
    -0.07
     crc
    -0.07
     gladly
    -0.07
    orda
    -0.07
     held
    -0.06
    Absolutely
    -0.06
     точно
    -0.06
    _closure
    -0.06
    试
    -0.06
    POSITIVE LOGITS
    arParams
    0.06
     frente
    0.06
    으로
    0.06
     gc
    0.06
    міністра
    0.06
    _is
    0.06
    ashire
    0.05
    >/',
    0.05
    İs
    0.05
    _actor
    0.05
    Act Density 0.006%

    No Known Activations