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

    Neuronpedia

    INDEX
    Explanations

    importing ui styles and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🫡
    0.47
    🫠
    0.45
    🫶
    0.43
    graded
    0.43
    🪄
    0.43
    🫢
    0.42
    🫣
    0.42
    🩶
    0.40
    arsenic
    0.40
    🥹
    0.40
    POSITIVE LOGITS
     useStyles
    0.76
     makeStyles
    0.70
    typeface
    0.59
    Paper
    0.53
     Typography
    0.52
    Typography
    0.51
     Toolbar
    0.50
     AppBar
    0.48
     cls
    0.48
     Paper
    0.47
    Act Density 0.002%

    No Known Activations