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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bson
    -0.07
    áo
    -0.07
    :str
    -0.07
    覚え
    -0.06
     So
    -0.06
     alguna
    -0.06
    .');
    -0.06
    zure
    -0.06
    載
    -0.06
     Baron
    -0.06
    POSITIVE LOGITS
    ETYPE
    0.08
    机关
    0.07
    white
    0.07
     App
    0.07
    矿
    0.07
     SCRIPT
    0.07
     Machine
    0.07
    Combine
    0.07
    High
    0.07
     kernel
    0.07
    Act Density 0.013%

    No Known Activations