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

    Neuronpedia

    INDEX
    Explanations

    section or list headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akt
    0.47
    ak
    0.46
    दित
    0.46
    ag
    0.46
    code
    0.42
    oul
    0.41
    ik
    0.41
    ang
    0.41
    ley
    0.41
    s
    0.41
    POSITIVE LOGITS
     অন্যতম
    0.45
     ঠে
    0.43
     surtout
    0.41
     kõige
    0.41
    <s>
    0.40
     сердца
    0.39
     insist
    0.39
     ιδια
    0.39
    關於
    0.38
     Panzer
    0.38
    Act Density 0.005%

    No Known Activations