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

    Neuronpedia

    INDEX
    Explanations

    negative conflict or competition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ometric
    0.41
     ہے
    0.39
    і
    0.34
    мы
    0.34
     важли
    0.34
     можно
    0.33
    то
    0.33
    ches
    0.33
    /
    0.33
    Д
    0.33
    POSITIVE LOGITS
     mismanagement
    0.50
     massacre
    0.48
     martyrs
    0.45
     billionaires
    0.45
     disgraced
    0.44
     speculators
    0.44
     empresarios
    0.44
     prostitutes
    0.44
     gangsters
    0.43
     disastrous
    0.43
    Act Density 0.032%

    No Known Activations