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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     gioc
    -0.07
    .Butter
    -0.07
    ollen
    -0.07
     Wooden
    -0.06
    vre
    -0.06
     Bauer
    -0.06
    (graph
    -0.06
    髮
    -0.06
    [,
    -0.06
     Mathematical
    -0.06
    POSITIVE LOGITS
    פרויק
    0.07
    ▰
    0.07
    可靠性
    0.07
    (rand
    0.07
     Tôi
    0.07
     NE
    0.07
    rema
    0.07
     Shemale
    0.07
     SWITCH
    0.07
    שיפור
    0.07
    Act Density 0.001%

    No Known Activations