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

    Neuronpedia

    INDEX
    Explanations

    date after period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fork
    0.98
     volatility
    0.96
     time
    0.93
     narrative
    0.90
     AWD
    0.90
     حسب
    0.88
     liquidity
    0.88
     dramatic
    0.87
    eight
    0.86
    requires
    0.85
    POSITIVE LOGITS
    ｵ
    0.93
    Xu
    0.89
     itibaren
    0.89
     Nurse
    0.88
     बचने
    0.84
    ।
    0.84
     adipis
    0.84
    欤
    0.84
    Empleado
    0.82
    겅
    0.80
    Act Density 0.032%

    No Known Activations