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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taipei
    -0.06
     doctrines
    -0.06
    如此
    -0.06
    ynch
    -0.06
    urnished
    -0.06
    .UseText
    -0.06
     absolut
    -0.06
     deter
    -0.06
    far
    -0.06
    ières
    -0.06
    POSITIVE LOGITS
     shortest
    0.07
    VICE
    0.07
     yerinde
    0.06
    學校
    0.06
     Jap
    0.06
    bell
    0.06
    DOCKER
    0.06
    ++)↵
    0.06
     ότι
    0.06
    =(
    0.06
    Act Density 0.092%

    No Known Activations