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

    Neuronpedia

    INDEX
    Explanations

    deterioration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Accessible
    -0.07
     traditions
    -0.06
    節
    -0.06
     XmlNode
    -0.06
     Christians
    -0.06
    -bl
    -0.06
     Hub
    -0.06
     naam
    -0.06
     nhánh
    -0.06
     seemingly
    -0.05
    POSITIVE LOGITS
     GRE
    0.09
     deterior
    0.09
     deterioration
    0.08
    ert
    0.07
     Litecoin
    0.07
     Dwight
    0.07
     prefers
    0.07
     Bert
    0.07
     وظ
    0.07
     fert
    0.07
    Act Density 0.007%

    No Known Activations