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

    Neuronpedia

    INDEX
    Explanations

    Amelia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    0.84
     grazing
    0.63
     on
    0.62
     guar
    0.60
     but
    0.59
     religious
    0.59
     DUI
    0.59
     URL
    0.59
    츈
    0.59
     analyzer
    0.57
    POSITIVE LOGITS
    ir
    0.74
    n
    0.70
    ozone
    0.69
    áme
    0.64
     scaleOf
    0.64
    remain
    0.63
     ద్వారా
    0.63
    trashButton
    0.62
    on
    0.62
     делаю
    0.62
    Act Density 0.001%

    No Known Activations