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

    Neuronpedia

    INDEX
    Explanations

    unlock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sevent
    -0.06
    ��
    -0.06
     ré
    -0.06
    (setting
    -0.06
     OV
    -0.06
     Station
    -0.06
    Serv
    -0.05
     dévelop
    -0.05
    Large
    -0.05
     상대
    -0.05
    POSITIVE LOGITS
    -we
    0.07
    albums
    0.07
    /com
    0.07
     dumps
    0.06
     <=>
    0.06
    andal
    0.06
    she
    0.06
    (comb
    0.06
     huy
    0.06
    ubl
    0.06
    Act Density 0.001%

    No Known Activations