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

    Neuronpedia

    INDEX
    Explanations

    rules and strategies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supply
    -0.08
     wyst
    -0.08
    /npm
    -0.07
     Kirst
    -0.07
    joining
    -0.07
    Joining
    -0.07
    ohl
    -0.07
     Kindle
    -0.07
     Kare
    -0.07
    -largest
    -0.07
    POSITIVE LOGITS
     designs
    0.10
    策略
    0.09
     Designing
    0.09
    -designed
    0.09
    一致
    0.09
     designers
    0.09
     designed
    0.09
     डिजाइन
    0.09
     desain
    0.09
     classifiers
    0.08
    Act Density 0.007%

    No Known Activations