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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ildren
    -0.06
     Selection
    -0.06
     ص
    -0.06
     rarity
    -0.06
     Cavaliers
    -0.06
     smelling
    -0.06
     possibility
    -0.06
     turnovers
    -0.06
    沒
    -0.06
    stadt
    -0.06
    POSITIVE LOGITS
    .HorizontalAlignment
    0.07
     зелен
    0.07
    StringRef
    0.07
     HC
    0.07
    CPF
    0.07
    (Channel
    0.06
    _LICENSE
    0.06
     Kiş
    0.06
    arbeit
    0.06
     UB
    0.06
    Act Density 0.003%

    No Known Activations