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

    Neuronpedia

    INDEX
    Explanations

    completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Architecture
    -0.08
    arr
    -0.07
    _PACK
    -0.07
     Assessment
    -0.07
    ursos
    -0.06
    .construct
    -0.06
     Imp
    -0.06
    tax
    -0.06
     مت
    -0.06
     traf
    -0.06
    POSITIVE LOGITS
    Completion
    0.08
     completion
    0.08
     breakout
    0.07
    งใน
    0.07
     چنین
    0.07
     Fireplace
    0.07
     semi
    0.06
    _completion
    0.06
    .when
    0.06
    :disable
    0.06
    Act Density 0.004%

    No Known Activations