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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adept
    -0.06
     shallow
    -0.06
     jit
    -0.06
    фік
    -0.06
    ">@
    -0.06
    Canadian
    -0.06
    ăng
    -0.06
    LOS
    -0.06
     starší
    -0.06
    ôn
    -0.06
    POSITIVE LOGITS
     LSTM
    0.07
     readFile
    0.06
    emails
    0.06
    喜
    0.06
    頃
    0.06
     معماری
    0.06
    _skin
    0.06
    053
    0.06
    對
    0.06
    ประถม
    0.06
    Act Density 0.004%

    No Known Activations