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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     democracy
    -0.08
    .UPDATE
    -0.07
    Ans
    -0.07
    _den
    -0.06
    .ind
    -0.06
     preference
    -0.06
     façon
    -0.06
     feminine
    -0.06
     반
    -0.06
    аних
    -0.06
    POSITIVE LOGITS
     JsonResult
    0.06
    _dbg
    0.06
    уст
    0.06
    findOrFail
    0.06
    UTF
    0.06
    $array
    0.05
     Jets
    0.05
    말
    0.05
     Duffy
    0.05
    ">'.$
    0.05
    Act Density 0.209%

    No Known Activations