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

    Neuronpedia

    INDEX
    Explanations

    script excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suscept
    -0.08
    .Nav
    -0.07
    谁都
    -0.07
    重点领域
    -0.07
    ineTransform
    -0.07
     objectType
    -0.07
     matplotlib
    -0.07
    .page
    -0.07
     stdout
    -0.07
     Witt
    -0.07
    POSITIVE LOGITS
    (fetch
    0.07
    mere
    0.07
     lifting
    0.07
    Happy
    0.07
    מוזיאון
    0.07
     redesign
    0.07
    Partition
    0.06
    _UNLOCK
    0.06
    .End
    0.06
    yards
    0.06
    Act Density 0.097%

    No Known Activations