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

    Neuronpedia

    INDEX
    Explanations

    uptake

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seaborn
    -0.08
     потому
    -0.07
    ीब
    -0.06
    تری
    -0.06
     PID
    -0.06
    یت
    -0.06
    ува
    -0.06
     junit
    -0.06
    ेत
    -0.06
    hawk
    -0.06
    POSITIVE LOGITS
    _fr
    0.07
     glanced
    0.06
     parsley
    0.06
     Israel
    0.06
     glGet
    0.06
    prom
    0.06
    Marvel
    0.06
    compress
    0.06
    {{$
    0.06
    dao
    0.06
    Act Density 0.039%

    No Known Activations