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

    Neuronpedia

    INDEX
    Explanations

    journal or department names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sapp
    1.07
     Hobart
    1.01
    pictured
    1.00
     témo
    1.00
     RTX
    0.98
    Ukrainian
    0.98
     Turner
    0.98
     Tec
    0.97
    Australian
    0.97
     Aten
    0.97
    POSITIVE LOGITS
    하자
    0.90
    ＝
    0.88
     voulais
    0.86
    รก
    0.85
     بحيث
    0.83
     käyttö
    0.83
     하자
    0.83
     법칙
    0.82
    스로
    0.81
     изучение
    0.79
    Act Density 0.094%

    No Known Activations