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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    species
    -0.07
    Ell
    -0.07
    behavior
    -0.07
     frustrated
    -0.07
    _pkt
    -0.07
     Lottery
    -0.07
     Imperial
    -0.07
     orders
    -0.07
    Park
    -0.06
    273
    -0.06
    POSITIVE LOGITS
    ()!=
    0.06
     QtCore
    0.06
    .ic
    0.06
     konkrét
    0.06
     ()
↵
    0.06
     зовніш
    0.06
    �
    0.06
    ("../../
    0.06
     disponibles
    0.06
    사랑
    0.06
    Act Density 0.044%

    No Known Activations