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

    Neuronpedia

    INDEX
    Explanations

    number state address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಬರುತ್ತ
    0.52
    👋
    0.46
     ორგანო
    0.46
    吃饭
    0.44
    秥
    0.44
    जी
    0.43
    نیا
    0.43
    朮
    0.43
    0.42
    SCHRAMM
    0.42
    POSITIVE LOGITS
     swapped
    0.51
     vineyards
    0.47
     marinas
    0.47
    0.47
     fillets
    0.45
     marinade
    0.44
     marin
    0.42
     exhaust
    0.41
     accounted
    0.41
     redeemed
    0.41
    Act Density 0.005%

    No Known Activations