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

    Neuronpedia

    INDEX
    Explanations

    decrease

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rb
    -0.08
     oud
    -0.07
    _PHY
    -0.07
    (None
    -0.06
     "#{
    -0.06
     hoping
    -0.06
    ObjectType
    -0.06
    uggling
    -0.06
    技術
    -0.06
     Wel
    -0.06
    POSITIVE LOGITS
     decrease
    0.17
     decreased
    0.16
     decreasing
    0.14
     decreases
    0.13
     Decre
    0.10
    Decre
    0.09
    rice
    0.09
     diminish
    0.08
     감
    0.08
    dataArray
    0.07
    Act Density 0.017%

    No Known Activations