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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     computers
    -0.07
     определ
    -0.07
    .getTable
    -0.07
     rocker
    -0.06
     Sevent
    -0.06
     drops
    -0.06
    鲁
    -0.06
    tro
    -0.06
     building
    -0.06
    (BigInteger
    -0.06
    POSITIVE LOGITS
    etik
    0.07
     behaving
    0.07
    ICollection
    0.07
     nord
    0.06
     Bakan
    0.06
     перв
    0.06
    ALLOC
    0.06
    steder
    0.06
     taraf
    0.06
    ѕ
    0.06
    Act Density 0.021%

    No Known Activations