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

    Neuronpedia

    INDEX
    Explanations

    at their own pace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ない
    0.30
     getters
    0.30
     sacrificial
    0.29
    летний
    0.29
     healers
    0.29
    ীম
    0.29
    ตัด
    0.29
     работает
    0.28
     showrooms
    0.28
     geotechnical
    0.28
    POSITIVE LOGITS
    incent
    0.28
    progress
    0.27
    poses
    0.27
    pose
    0.25
     daytime
    0.25
    你怎么
    0.25
    thon
    0.25
    bos
    0.25
    Spanish
    0.25
    rib
    0.24
    Act Density 0.003%

    No Known Activations