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

    Neuronpedia

    INDEX
    Explanations

    contrasting with expected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或
    0.51
     или
    0.49
    ेंट
    0.48
    ү
    0.44
    или
    0.44
    或其他
    0.43
     Даже
    0.43
    om
    0.42
    때
    0.42
     அல்லது
    0.41
    POSITIVE LOGITS
     vzděl
    0.50
     സൃഷ്ട
    0.48
     föränd
    0.48
     docente
    0.48
     misfort
    0.46
     bunga
    0.46
     zainteres
    0.46
     sejak
    0.45
     queria
    0.44
     artt
    0.44
    Act Density 0.024%

    No Known Activations