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

    Neuronpedia

    INDEX
    Explanations

    gradient boosting, XGBoost, GBM

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reflection
    0.90
     youth
    0.89
     dietitian
    0.89
    ೀವ
    0.87
    ीकरण
    0.86
    тном
    0.85
    י
    0.84
    ీ
    0.84
     sient
    0.83
     varn
    0.82
    POSITIVE LOGITS
    Когда
    1.24
    Му
    1.16
    Бо
    1.14
    Если
    1.11
    Про
    1.07
    Ра
    1.06
    Этот
    1.06
    До
    1.05
    Ку
    1.05
    package
    1.00
    Act Density 0.005%

    No Known Activations