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

    Neuronpedia

    INDEX
    Explanations

    restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ันเป
    -0.06
     bad
    -0.06
     Bad
    -0.06
     التق
    -0.06
     круг
    -0.06
    _red
    -0.06
     deferred
    -0.05
     nas
    -0.05
    .Long
    -0.05
     busy
    -0.05
    POSITIVE LOGITS
    发出
    0.07
    iership
    0.07
    рук
    0.06
    요
    0.06
     киш
    0.06
    parameter
    0.06
     Specifications
    0.06
     eski
    0.06
     haven
    0.06
     Allocation
    0.06
    Act Density 0.001%

    No Known Activations