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

    Neuronpedia

    INDEX
    Explanations

    Register

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    规模最大
    -0.07
     jan
    -0.07
    surf
    -0.07
     cust
    -0.07
     dout
    -0.07
    黄河
    -0.07
    Blue
    -0.07
    BCM
    -0.07
    index
    -0.07
    download
    -0.07
    POSITIVE LOGITS
    orthand
    0.07
    JECTED
    0.07
     employ
    0.07
     throughout
    0.07
    NASA
    0.07
    提高
    0.06
     ####
    0.06
     accounts
    0.06
    ♻
    0.06
    ancements
    0.06
    Act Density 0.001%

    No Known Activations