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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \F
    -0.07
    -la
    -0.06
     кос
    -0.06
     Ensemble
    -0.06
    _nl
    -0.06
     mejor
    -0.06
    -f
    -0.06
     кан
    -0.06
     Municipal
    -0.06
    _LEN
    -0.06
    POSITIVE LOGITS
    .Skin
    0.07
     Unless
    0.07
    iyor
    0.07
     BeautifulSoup
    0.06
     merkez
    0.06
    워크
    0.06
     hookers
    0.06
     BaseModel
    0.06
     зрения
    0.06
    (seed
    0.06
    Act Density 0.006%

    No Known Activations