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

    Neuronpedia

    INDEX
    Explanations

    ui styling in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ிடம்
    0.42
     NavigationView
    0.41
     જતા
    0.39
    ｱ
    0.39
     Baillargeon
    0.38
     مجبور
    0.38
    starttime
    0.37
    نگی
    0.36
    wxT
    0.36
    <unused36>
    0.36
    POSITIVE LOGITS
     styles
    0.71
    Styles
    0.69
    styles
    0.67
     Styles
    0.63
     estilos
    0.62
     useStyles
    0.54
    Style
    0.53
     스타일
    0.50
    ={
    0.50
     शैली
    0.49
    Act Density 0.003%

    No Known Activations