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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     metropolitan
    -0.08
     DNS
    -0.07
    environments
    -0.07
    existence
    -0.07
     boils
    -0.07
     TAX
    -0.07
     fast
    -0.07
    /profile
    -0.06
    ModelState
    -0.06
     Fully
    -0.06
    POSITIVE LOGITS
    .transpose
    0.07
     Leia
    0.07
    +l
    0.07
     billboard
    0.06
    ⏝
    0.06
    ERT
    0.06
    .Reflection
    0.06
     seventh
    0.06
     characters
    0.06
     verbally
    0.06
    Act Density 0.001%

    No Known Activations