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
     healthcare
    -0.08
    .Configure
    -0.08
     Confirmation
    -0.08
     scanf
    -0.08
    ┨
    -0.07
    重要的
    -0.07
    蚄
    -0.07
     Câmara
    -0.07
    _COMMAND
    -0.07
    _path
    -0.07
    POSITIVE LOGITS
    ably
    0.08
    精益求
    0.06
    trä
    0.06
    odes
    0.06
    ],&
    0.06
    ropical
    0.06
    ities
    0.06
    pects
    0.06
    enu
    0.06
    getAs
    0.06
    Act Density 0.001%

    No Known Activations