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

    Neuronpedia

    INDEX
    Explanations

    excellent invalidate remove huge extremely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rases
    0.46
    ively
    0.45
     ethereal
    0.45
    Sicilian
    0.45
    acher
    0.43
    šić
    0.43
    :'],
    0.43
    Violet
    0.43
    CHCl
    0.42
     quadrature
    0.42
    POSITIVE LOGITS
    數據
    0.49
    村
    0.48
     製造
    0.48
     工作
    0.46
    工
    0.46
     OF
    0.46
     Sustainable
    0.45
    裝置
    0.45
     машины
    0.44
    可持续
    0.43
    Act Density 0.001%

    No Known Activations