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

    Neuronpedia

    INDEX
    Explanations

    new app creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    usual
    0.34
    seen
    0.33
     usual
    0.32
    bathing
    0.32
     treating
    0.32
    separ
    0.32
     fran
    0.32
     regular
    0.31
    treated
    0.31
     فصل
    0.31
    POSITIVE LOGITS
    MyApp
    0.68
    myapp
    0.68
    我的
    0.60
     MyApp
    0.59
     my
    0.58
     MyApplication
    0.55
     My
    0.55
    My
    0.55
    my
    0.51
     আমার
    0.51
    Act Density 0.017%

    No Known Activations