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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maries
    -0.07
    reece
    -0.07
    xef
    -0.07
    ruz
    -0.07
    ASTER
    -0.07
     ReferentialAction
    -0.06
    ainties
    -0.06
     prescription
    -0.06
    .bin
    -0.06
    heet
    -0.06
    POSITIVE LOGITS
    磨
    0.07
    导向
    0.07
    DM
    0.06
    坡
    0.06
     regular
    0.06
    牌
    0.06
     fontWeight
    0.06
    私
    0.06
     pioneer
    0.06
    寨
    0.06
    Act Density 0.090%

    No Known Activations