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

    Neuronpedia

    INDEX
    Explanations

    Prediction accuracy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Desktop
    -0.07
     السي
    -0.07
    итив
    -0.06
     cater
    -0.06
     naar
    -0.06
    송
    -0.06
     rollers
    -0.06
     pymongo
    -0.06
     như
    -0.06
     curious
    -0.06
    POSITIVE LOGITS
    order
    0.06
    balances
    0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
    
    0.06
    multiple
    0.06
    (repository
    0.06
     RS
    0.06
     sewing
    0.06
    quina
    0.06
    VM
    0.06
    Act Density 0.011%

    No Known Activations