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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -0.62
     disambiguazione
    -0.51
    Abp
    -0.49
     del
    -0.48
    <%
    -0.48
    ])):
    -0.46
    thâu
    -0.46
    orianCalendar
    -0.45
    springframework
    -0.45
     createState
    -0.45
    POSITIVE LOGITS
     وصلة
    0.63
    Rhestr
    0.56
    chong
    0.56
    gdx
    0.54
     wri
    0.54
     strix
    0.54
    DrawerToggle
    0.53
    cheibe
    0.53
     Dax
    0.53
    Хьажоргаш
    0.51
    Act Density 0.000%

    No Known Activations