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

    Neuronpedia

    INDEX
    Explanations

    involved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ější
    -0.09
    ัด
    -0.08
    December
    -0.08
    éra
    -0.07
     outra
    -0.07
     thirst
    -0.07
     pension
    -0.07
    нен
    -0.07
     dette
    -0.07
     accommodate
    -0.07
    POSITIVE LOGITS
     involvement
    0.10
     involved
    0.09
     Inv
    0.08
     Ivan
    0.08
    луги
    0.08
    涉
    0.07
     Иванов
    0.07
    .Work
    0.07
    Under
    0.07
    help
    0.07
    Act Density 0.016%

    No Known Activations