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

    Neuronpedia

    INDEX
    Explanations

    Chinese characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    12
    -0.08
    �
    -0.07
     güzel
    -0.07
     závod
    -0.07
     Tại
    -0.07
    Glass
    -0.07
     bridge
    -0.07
    489
    -0.07
    win
    -0.07
     tìm
    -0.07
    POSITIVE LOGITS
     Jacob
    0.10
    Jacob
    0.09
     Jake
    0.08
    Jake
    0.08
     didn
    0.08
     Haley
    0.07
     Jonathan
    0.07
     Fah
    0.07
     Hannah
    0.07
     Abraham
    0.07
    Act Density 0.108%

    No Known Activations