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

    Neuronpedia

    INDEX
    Explanations

    IRS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    斗
    -0.09
     Chap
    -0.08
     airstrikes
    -0.07
    远洋
    -0.07
     cum
    -0.07
     mid
    -0.07
    -that
    -0.07
    槽
    -0.07
     Jul
    -0.07
    _trip
    -0.07
    POSITIVE LOGITS
     IRS
    0.08
    deprecated
    0.07
    诂
    0.07
    HH
    0.07
     Surrey
    0.07
     assigning
    0.07
    MESSAGE
    0.07
    _ws
    0.07
    掬
    0.07
     lobbyists
    0.07
    Act Density 0.001%

    No Known Activations