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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intervened
    -0.07
    谁
    -0.07
    ックス
    -0.07
    ча
    -0.07
    iston
    -0.07
    vat
    -0.06
    LAN
    -0.06
     Fluent
    -0.06
     א
    -0.06
     Deleting
    -0.06
    POSITIVE LOGITS
    .nb
    0.07
    gMaps
    0.07
    になった
    0.07
    .writeValue
    0.07
     ={
    0.07
     دستگاه
    0.06
     karış
    0.06
    )));↵
    0.06
    `"]↵
    0.06
    __);↵
    0.06
    Act Density 0.042%

    No Known Activations