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

    Neuronpedia

    INDEX
    Explanations

    Exclamations and dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Medicine
    -0.07
     medicine
    -0.06
    241
    -0.06
     hex
    -0.06
     k
    -0.06
     BeautifulSoup
    -0.06
    alk
    -0.06
     Pant
    -0.06
    }",
    -0.06
    EMA
    -0.06
    POSITIVE LOGITS
    credentials
    0.07
    .MiddleRight
    0.06
     Jewelry
    0.06
    ิดต
    0.06
     여
    0.06
     °
    0.06
     soak
    0.06
     Marketable
    0.06
     вос
    0.06
     коман
    0.06
    Act Density 0.117%

    No Known Activations