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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跨越
    -0.07
    Nous
    -0.07
    Register
    -0.07
    >This
    -0.07
    chan
    -0.06
    ßen
    -0.06
    新春
    -0.06
    .getKey
    -0.06
     facile
    -0.06
    -boot
    -0.06
    POSITIVE LOGITS
    現實
    0.07
    廠
    0.07
    桅
    0.07
    芏
    0.07
     Romanian
    0.07
    셑
    0.07
    镞
    0.07
    霰
    0.07
    疟
    0.06
     infield
    0.06
    Act Density 0.017%

    No Known Activations