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

    Neuronpedia

    INDEX
    Explanations

    Scientific properties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Price
    -0.07
     BYTE
    -0.07
     Jennifer
    -0.07
    _space
    -0.07
    (prediction
    -0.07
     blend
    -0.06
     Muk
    -0.06
    Row
    -0.06
     キャ
    -0.06
     люд
    -0.06
    POSITIVE LOGITS
     overlooking
    0.06
    leşme
    0.06
    hoa
    0.06
     групи
    0.06
    _Category
    0.06
    .toArray
    0.06
     Adresse
    0.06
     antis
    0.06
     kendini
    0.06
    �a
    0.06
    Act Density 0.045%

    No Known Activations