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

    Neuronpedia

    INDEX
    Explanations

    proportional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Picker
    -0.07
     memories
    -0.06
     sagt
    -0.06
     userInfo
    -0.06
    _SID
    -0.06
    ecc
    -0.06
     mimo
    -0.06
    晶
    -0.06
     تجربه
    -0.06
    InnerHTML
    -0.06
    POSITIVE LOGITS
     жінок
    0.07
    UnderTest
    0.06
    +↵↵
    0.06
    (())↵
    0.06
    -under
    0.06
    ॉय
    0.06
     plast
    0.06
    (i
    0.06
    =title
    0.06
    rocessing
    0.06
    Act Density 0.037%

    No Known Activations