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

    Neuronpedia

    INDEX
    Explanations

    client

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lifts
    -0.06
    serious
    -0.06
     取
    -0.06
     тов
    -0.06
    persistent
    -0.06
     mocker
    -0.06
     зн
    -0.06
    ่าน
    -0.05
    стр
    -0.05
    ＊
    -0.05
    POSITIVE LOGITS
    áng
    0.07
     Phân
    0.07
    ,www
    0.07
    <vector
    0.07
     Intel
    0.07
     Hibernate
    0.07
    /target
    0.06
     villa
    0.06
     Richie
    0.06
    .UUID
    0.06
    Act Density 0.209%

    No Known Activations