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

    Neuronpedia

    INDEX
    Explanations

    project implementation structure and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     physicians
    0.39
    ographers
    0.39
     ちゃっ
    0.38
    antibodies
    0.38
     attorneys
    0.37
    wifery
    0.37
    aguan
    0.37
     autoch
    0.37
    rogenic
    0.37
    ocytic
    0.37
    POSITIVE LOGITS
     구현
    0.93
     implementar
    0.88
     implement
    0.87
     Implement
    0.86
     implemented
    0.84
     implementación
    0.84
    Implementing
    0.84
    实现
    0.83
     implementing
    0.83
    Implement
    0.83
    Act Density 0.058%

    No Known Activations