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

    Neuronpedia

    INDEX
    Explanations

    .state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '::
    -0.07
     deserves
    -0.07
     männer
    -0.07
     videa
    -0.06
     nást
    -0.06
    "What
    -0.06
     downt
    -0.06
     Pir
    -0.06
    "To
    -0.06
    -b
    -0.06
    POSITIVE LOGITS
    geois
    0.08
    asal
    0.06
     selling
    0.06
     bombers
    0.06
     chats
    0.06
    olesterol
    0.06
     uneven
    0.06
    аж
    0.06
     دولت
    0.06
    .blue
    0.06
    Act Density 0.001%

    No Known Activations