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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нич
    -0.07
    _dl
    -0.06
    000
    -0.06
    outputs
    -0.06
     نور
    -0.06
     누
    -0.06
    pagen
    -0.06
    -V
    -0.06
     quien
    -0.06
     Americas
    -0.06
    POSITIVE LOGITS
    ЮЛ
    0.06
     librarian
    0.06
     BI
    0.06
     берем
    0.06
    іб
    0.06
    ierre
    0.06
     XB
    0.06
     représ
    0.06
    splice
    0.06
     IICIII
    0.06
    Act Density 0.156%

    No Known Activations