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

    Neuronpedia

    INDEX
    Explanations

    express

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    西南
    -0.08
    علاقات
    -0.07
    Admin
    -0.07
    ARDS
    -0.07
     ventana
    -0.07
    中标
    -0.07
    (Environment
    -0.07
     mapStateToProps
    -0.07
     Pakistan
    -0.07
     posição
    -0.07
    POSITIVE LOGITS
    whereIn
    0.07
     ✔
    0.07
    ☠
    0.07
     nó
    0.06
    ĩnh
    0.06
    mentor
    0.06
    ₫
    0.06
     IDisposable
    0.06
    %'↵
    0.06
     Mig
    0.06
    Act Density 0.027%

    No Known Activations