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

    Neuronpedia

    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cols
    -0.06
     rods
    -0.06
     Fare
    -0.06
     impuls
    -0.06
    icter
    -0.06
    ěle
    -0.06
     ConnectionState
    -0.06
     เขต
    -0.06
    apis
    -0.06
     떨어
    -0.06
    POSITIVE LOGITS
    U
    0.07
     outraged
    0.07
     bò
    0.07
     těchto
    0.07
     삭제
    0.07
    swing
    0.07
     addUser
    0.06
     zejména
    0.06
    User
    0.06
    [selected
    0.06
    Act Density 0.021%

    No Known Activations