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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     từ
    -0.06
     obed
    -0.06
     Rao
    -0.06
    398
    -0.06
    _Exception
    -0.06
     collected
    -0.06
    cakes
    -0.06
    Ro
    -0.06
    潮
    -0.06
    VT
    -0.06
    POSITIVE LOGITS
    kee
    0.06
    stock
    0.06
     Aviation
    0.06
    χη
    0.06
    (cls
    0.06
     化
    0.06
    EG
    0.06
    ρω
    0.06
    productos
    0.06
     Pyongyang
    0.06
    Act Density 0.000%

    No Known Activations