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

    Neuronpedia

    INDEX
    Explanations

    lateral

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pix
    -0.07
     agg
    -0.07
     endorsing
    -0.07
    高兴
    -0.07
    руб
    -0.07
    ን
    -0.07
    满满的
    -0.07
     unfore
    -0.07
     ries
    -0.07
     мар
    -0.06
    POSITIVE LOGITS
    移民
    0.07
    秩
    0.07
    ypsum
    0.07
    XI
    0.07
     Classical
    0.06
    🏫
    0.06
    сло
    0.06
    水泵
    0.06
    Wow
    0.06
    Russia
    0.06
    Act Density 0.009%

    No Known Activations