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

    Neuronpedia

    INDEX
    Explanations

    instructions to complete tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⺆
    1.00
    BrNO
    0.92
     mètres
    0.90
     chúc
    0.89
     )\
    0.88
    TrackAngle
    0.86
    ุ้น
    0.85
    )}')
    0.85
     \%)$.
    0.84
     प्रोसेसर
    0.84
    POSITIVE LOGITS
    с
    0.88
    s
    0.85
     not
    0.71
    то
    0.71
     обу
    0.67
    ando
    0.65
     un
    0.64
    por
    0.64
     Complex
    0.64
    BE
    0.62
    Act Density 0.002%

    No Known Activations