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

    Neuronpedia

    INDEX
    Explanations

    Santiago Peña

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ports
    0.39
     ऐप
    0.38
    ::*;
    0.36
     correa
    0.36
    ligen
    0.36
     puertos
    0.36
     parmes
    0.36
     merr
    0.36
    pheus
    0.36
     perpendicular
    0.35
    POSITIVE LOGITS
     Dudley
    0.43
     renderings
    0.39
    퉁
    0.39
     academics
    0.38
     FPS
    0.38
     Tully
    0.38
    āti
    0.37
    zetten
    0.37
     FTIR
    0.37
     تھا
    0.37
    Act Density 0.001%

    No Known Activations