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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    luk
    -0.07
    avorites
    -0.07
    embourg
    -0.07
    Feed
    -0.07
    .helper
    -0.06
     kost
    -0.06
    代
    -0.06
    Enable
    -0.06
    .persistence
    -0.06
     Fey
    -0.06
    POSITIVE LOGITS
    memiş
    0.07
    26
    0.06
     ii
    0.06
    fs
    0.06
     ;;↵
    0.06
     notion
    0.06
     Earth
    0.06
    elle
    0.06
     sai
    0.06
     Clement
    0.06
    Act Density 0.004%

    No Known Activations