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

    Neuronpedia

    INDEX
    Explanations

    current leaders and their titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鼍
    0.37
    细菌
    0.36
    Imidazole
    0.35
    误差
    0.35
     연구
    0.34
    韫
    0.34
    MaxIntensity
    0.33
     badań
    0.33
     Sereth
    0.33
     założ
    0.33
    POSITIVE LOGITS
     president
    0.42
     President
    0.41
     politicians
    0.40
     incumbent
    0.40
    president
    0.39
    President
    0.39
    new
    0.39
     президента
    0.38
     ministers
    0.36
    current
    0.36
    Act Density 0.043%

    No Known Activations