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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elo
    -0.08
     TextView
    -0.07
    Concern
    -0.07
    뇗
    -0.07
    AVOR
    -0.07
    随时随
    -0.07
    imers
    -0.06
    泅
    -0.06
    عسكر
    -0.06
     euch
    -0.06
    POSITIVE LOGITS
    があった
    0.07
     Assistant
    0.07
    (split
    0.07
    .\"
    0.07
    rió
    0.07
    remain
    0.06
     NotFound
    0.06
    -option
    0.06
    坜
    0.06
     office
    0.06
    Act Density 0.050%

    No Known Activations