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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engineers
    -0.07
     Radio
    -0.07
     to
    -0.06
     Andy
    -0.06
    ill
    -0.06
     To
    -0.06
     engineering
    -0.06
     declined
    -0.06
     engineer
    -0.06
    фт
    -0.06
    POSITIVE LOGITS
    umped
    0.07
    Swift
    0.07
    .CreateInstance
    0.06
    ですね
    0.06
     články
    0.06
     할인
    0.06
    유머
    0.06
    م
    0.06
    ,private
    0.06
     canActivate
    0.06
    Act Density 0.054%

    No Known Activations