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

    Neuronpedia

    INDEX
    Explanations

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vertices
    -0.07
    槛
    -0.07
    *S
    -0.06
    一间
    -0.06
     ConnectionState
    -0.06
     taxpayer
    -0.06
     per
    -0.06
     из
    -0.06
     deltaTime
    -0.06
    毕业生
    -0.06
    POSITIVE LOGITS
    南海
    0.08
     gist
    0.07
    婍
    0.07
     doctoral
    0.07
     alta
    0.07
    gaard
    0.07
    كهرباء
    0.07
    是国内
    0.07
    秘书长
    0.07
    gary
    0.07
    Act Density 0.048%

    No Known Activations