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

    Neuronpedia

    INDEX
    Explanations

    awards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pan
    -0.06
     Sala
    -0.06
     Lista
    -0.06
    Util
    -0.05
    бач
    -0.05
     shuttle
    -0.05
    baru
    -0.05
    Seller
    -0.05
    _lot
    -0.05
    datagrid
    -0.05
    POSITIVE LOGITS
    �
    0.08
     comprise
    0.07
     IEntity
    0.07
    лаш
    0.07
     paras
    0.07
    νομα
    0.07
     seis
    0.07
    __(*
    0.07
    ///<
    0.07
     inception
    0.06
    Act Density 0.027%

    No Known Activations