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

    Neuronpedia

    INDEX
    Explanations

    Code settings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Frameworks
    -0.07
     skutečně
    -0.06
    ults
    -0.06
    ิย
    -0.06
     Endpoint
    -0.06
    лова
    -0.06
    Recv
    -0.06
    ITableView
    -0.06
    owego
    -0.06
     Essays
    -0.06
    POSITIVE LOGITS
    /world
    0.08
    /end
    0.07
     exchanges
    0.06
    ishes
    0.06
    沙
    0.06
    ipel
    0.06
    igans
    0.06
     góp
    0.06
     tercih
    0.06
     maç
    0.06
    Act Density 0.011%

    No Known Activations