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

    Neuronpedia

    INDEX
    Explanations

    membership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LIN
    -0.07
     sır
    -0.07
     BU
    -0.06
     conservatives
    -0.06
    _gift
    -0.06
     Sciences
    -0.06
     Steven
    -0.06
    그러
    -0.06
    スペ
    -0.06
    judge
    -0.06
    POSITIVE LOGITS
     member
    0.07
     Member
    0.07
     {},↵
    0.07
     members
    0.07
     membership
    0.07
    Ok
    0.06
    Member
    0.06
     Golf
    0.06
     Membership
    0.06
    .ip
    0.06
    Act Density 0.021%

    No Known Activations