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

    Neuronpedia

    INDEX
    Explanations

    actors performing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    闹
    0.44
    니아
    0.44
    yy
    0.43
     થાય
    0.43
     条件
    0.42
     Governo
    0.42
    yao
    0.41
    orno
    0.41
    òa
    0.40
    viii
    0.39
    POSITIVE LOGITS
    actors
    0.51
     actores
    0.51
     actors
    0.50
     aldı
    0.47
     así
    0.46
     Actors
    0.45
     ardından
    0.44
     hechos
    0.44
    rators
    0.43
    ским
    0.43
    Act Density 0.000%

    No Known Activations