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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .qml
    -0.07
    �
    -0.07
     courseId
    -0.06
    过
    -0.06
     губ
    -0.06
    -route
    -0.06
     tourist
    -0.06
     kl
    -0.06
     pry
    -0.06
     UserId
    -0.06
    POSITIVE LOGITS
    rena
    0.06
    trans
    0.06
    _street
    0.06
     Renew
    0.06
     success
    0.06
          
↵
    0.06
    entities
    0.06
     mature
    0.06
     VX
    0.06
     toughest
    0.06
    Act Density 0.004%

    No Known Activations