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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Part
    -0.07
    .eye
    -0.06
     ejercicio
    -0.06
    meye
    -0.06
    צד
    -0.06
    失业
    -0.06
     económica
    -0.06
    ).*
    -0.06
     part
    -0.06
    earn
    -0.06
    POSITIVE LOGITS
    伙伴关系
    0.08
    ;'↵
    0.08
    (Vertex
    0.07
     בשל
    0.07
     Интер
    0.07
     mav
    0.07
    岜
    0.07
    荞
    0.07
    NullOr
    0.07
     Сейчас
    0.07
    Act Density 0.207%

    No Known Activations