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

    Neuronpedia

    INDEX
    Explanations

    USSR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     witnessed
    -0.07
     Overwatch
    -0.07
     Specifications
    -0.07
    patches
    -0.06
    Spanish
    -0.06
    +A
    -0.06
    instances
    -0.06
     './
    -0.06
     broadcast
    -0.06
     Communist
    -0.06
    POSITIVE LOGITS
     cpp
    0.06
    /todo
    0.06
    _sz
    0.06
     onwards
    0.06
    ENCH
    0.06
     내가
    0.06
    .eth
    0.06
     dotenv
    0.06
     за
    0.06
    κει
    0.06
    Act Density 0.000%

    No Known Activations