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

    Neuronpedia

    INDEX
    Explanations

    human error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.15
    in
    1.02
    e
    1.02
    v
    1.01
    s
    1.00
    i
    0.98
    o
    0.92
    f
    0.92
    b
    0.87
    n
    0.86
    POSITIVE LOGITS
     ставак
    0.64
     nave
    0.63
     이미지
    0.63
    →</
    0.62
     знать
    0.62
     হইয়াছিল
    0.62
     сне
    0.62
    ेश्वर
    0.61
     করিতেছিল
    0.61
     выполнять
    0.61
    Act Density 0.005%

    No Known Activations