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

    Neuronpedia

    INDEX
    Explanations

    honest, mutual, bush, audio, strengths, not pay, amount

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     συν
    0.55
     illeg
    0.48
    úblic
    0.47
     By
    0.46
     нови
    0.45
     मेहमान
    0.45
     Continent
    0.45
     রীতি
    0.45
    botones
    0.45
     Endangered
    0.44
    POSITIVE LOGITS
    г
    0.54
    нося
    0.53
    서
    0.52
    етка
    0.51
    е
    0.51
    ки
    0.48
    ли
    0.48
    اج
    0.46
    лі
    0.45
    وف
    0.45
    Act Density 0.013%

    No Known Activations