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

    Neuronpedia

    INDEX
    Explanations

    standing or stand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.94
    ch
    0.88
    на
    0.80
    se
    0.74
    ll
    0.73
    to
    0.72
    th
    0.71
    she
    0.71
    bí
    0.70
    và
    0.70
    POSITIVE LOGITS
     standing
    1.02
     Standing
    1.01
     Stand
    0.99
     debout
    0.96
     खड़ा
    0.90
     ovation
    0.87
     berdiri
    0.87
     STAND
    0.86
     stand
    0.85
     खड़े
    0.84
    Act Density 0.016%

    No Known Activations