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

    Neuronpedia

    INDEX
    Explanations

    academic/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abbo
    -0.07
     concludes
    -0.06
     чего
    -0.06
    Refreshing
    -0.06
     bakeka
    -0.06
    ירוע
    -0.06
     dị
    -0.06
     Prometheus
    -0.06
    един
    -0.06
    ፖ
    -0.06
    POSITIVE LOGITS
     tend
    0.08
     新
    0.08
     Trends
    0.08
     Fundamental
    0.08
    的趋势
    0.08
    \xb
    0.07
    压
    0.07
     денег
    0.07
    可用
    0.07
    理想
    0.07
    Act Density 0.318%

    No Known Activations