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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XCTest
    -0.07
    -thumbnails
    -0.07
    ルド
    -0.07
    مان
    -0.06
     Investment
    -0.06
    سام
    -0.06
     etwas
    -0.06
    alarından
    -0.06
    etim
    -0.06
     Mùa
    -0.06
    POSITIVE LOGITS
     businesses
    0.06
     Pé
    0.06
     WC
    0.06
     Jesse
    0.06
     obsessive
    0.06
    _delete
    0.06
    xAE
    0.06
     su
    0.06
     paints
    0.06
     historically
    0.06
    Act Density 0.031%

    No Known Activations