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

    Neuronpedia

    INDEX
    Explanations

    confirm acknowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.51
     mengenai
    0.47
     Xun
    0.47
     Hayley
    0.47
    èvre
    0.46
     Seasonal
    0.46
    n
    0.46
     Live
    0.46
    g
    0.45
    bing
    0.45
    POSITIVE LOGITS
    abilidades
    0.47
    ﺬ
    0.46
     панели
    0.45
    缅
    0.44
    ટ્સ
    0.44
    党
    0.44
    ﺀ
    0.43
    이스
    0.43
    虑
    0.43
    炬
    0.43
    Act Density 0.004%

    No Known Activations