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

    Neuronpedia

    INDEX
    Explanations

    bundle framework component security google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喙
    0.51
     heifers
    0.47
     bushels
    0.46
     rougeâtres
    0.43
     arrondies
    0.42
    ophones
    0.42
    diyl
    0.42
     radiographs
    0.41
    aretro
    0.41
     selfies
    0.41
    POSITIVE LOGITS
     Gobierno
    0.50
    ת
    0.49
     Agencia
    0.49
     Desarrollo
    0.48
     BrowserModule
    0.48
    功能
    0.47
     Government
    0.47
    פ
    0.47
    機能
    0.46
     Deploy
    0.46
    Act Density 0.001%

    No Known Activations