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

    Neuronpedia

    INDEX
    Explanations

    Array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oferta
    -0.07
     números
    -0.07
     enfermed
    -0.07
     Nobody
    -0.07
    ubble
    -0.07
    Telefone
    -0.06
    出版
    -0.06
     comport
    -0.06
     thought
    -0.06
    Ni
    -0.06
    POSITIVE LOGITS
    faq
    0.06
    .sim
    0.06
    (lon
    0.06
     повинен
    0.06
     VID
    0.06
     pepp
    0.06
    .SpringBootTest
    0.06
    ▏▏
    0.06
    -has
    0.06
    alerts
    0.06
    Act Density 0.006%

    No Known Activations