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

    Neuronpedia

    INDEX
    Explanations

    current wireless and AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Con
    0.53
     пі
    0.51
     Con
    0.51
     яй
    0.49
     т
    0.48
     be
    0.47
    prova
    0.47
    gris
    0.46
     доб
    0.46
    CreationFailed
    0.45
    POSITIVE LOGITS
     celebrates
    0.55
     playlist
    0.51
     resumes
    0.48
     spectacle
    0.46
     cosmopolitan
    0.45
     choreographed
    0.45
     }.
    0.45
     bridesmaids
    0.45
     सुपरस्टार
    0.44
     )
    0.43
    Act Density 0.001%

    No Known Activations