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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ijkl
    -0.07
    .projects
    -0.07
     Saudis
    -0.07
     Another
    -0.07
     chicas
    -0.07
     desarrollo
    -0.06
    .uuid
    -0.06
     imaginary
    -0.06
     SharePoint
    -0.06
    Another
    -0.06
    POSITIVE LOGITS
     вб
    0.07
     dod
    0.06
     то
    0.06
    ervention
    0.06
    จำก
    0.06
     kW
    0.06
    creenshot
    0.06
     bank
    0.06
     offensive
    0.06
    -Jan
    0.06
    Act Density 0.034%

    No Known Activations