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

    Neuronpedia

    INDEX
    Explanations

    -year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moon
    -0.07
     hàng
    -0.07
     ма
    -0.06
     Παν
    -0.06
     раб
    -0.06
     tariffs
    -0.06
     dd
    -0.06
     EntityManager
    -0.06
    .channels
    -0.06
    (Grid
    -0.06
    POSITIVE LOGITS
     eser
    0.07
    AIM
    0.06
    .Class
    0.06
     educated
    0.06
    iges
    0.06
    _bloc
    0.06
    ’i
    0.06
     sare
    0.06
     HAVE
    0.06
    -g
    0.06
    Act Density 0.029%

    No Known Activations