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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Diff
    -0.08
    images
    -0.07
    iyorlar
    -0.07
     Overview
    -0.07
    arta
    -0.07
     publi
    -0.07
    enario
    -0.06
    _diff
    -0.06
     sect
    -0.06
    /types
    -0.06
    POSITIVE LOGITS
    ↵↵    ↵
    0.06
    }.
    0.06
    ด
    0.06
     orbs
    0.06
     Karachi
    0.06
     grand
    0.06
     Ledger
    0.06
    .${
    0.06
     bức
    0.06
    院
    0.06
    Act Density 0.013%

    No Known Activations