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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "$(
    -0.07
     sane
    -0.07
    (suite
    -0.06
     Clown
    -0.06
    щ
    -0.06
    Indented
    -0.06
    alara
    -0.06
     schön
    -0.06
    $id
    -0.06
    енный
    -0.06
    POSITIVE LOGITS
    外
    0.06
    И
    0.06
     ranking
    0.06
    ARGV
    0.06
     προσ
    0.06
    mittel
    0.06
    (expression
    0.06
     Egypt
    0.06
     Require
    0.06
    .Cmd
    0.06
    Act Density 0.033%

    No Known Activations