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

    Neuronpedia

    INDEX
    Explanations

    code, data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotics
    -0.07
    .yang
    -0.07
     owned
    -0.07
     JR
    -0.06
     Coding
    -0.06
    rase
    -0.06
     leases
    -0.06
    奔
    -0.06
     Styled
    -0.06
     zůst
    -0.06
    POSITIVE LOGITS
    （笑
    0.08
     bullet
    0.06
    Nintendo
    0.06
    тів
    0.06
    -complete
    0.06
    чень
    0.06
     Totally
    0.06
    全球
    0.06
     phenotype
    0.06
    道路
    0.06
    Act Density 0.003%

    No Known Activations