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

    Neuronpedia

    INDEX
    Explanations

    player

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruku
    -0.07
     اولین
    -0.07
     журн
    -0.06
    rog
    -0.06
     чет
    -0.06
    يو
    -0.06
     svůj
    -0.06
     саме
    -0.06
    фров
    -0.06
    曼
    -0.06
    POSITIVE LOGITS
     PAGE
    0.07
     nav
    0.07
     nude
    0.07
    432
    0.07
    367
    0.07
    686
    0.07
    pkg
    0.07
     coordinating
    0.06
    (socket
    0.06
    マ
    0.06
    Act Density 0.000%

    No Known Activations