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

    Neuronpedia

    INDEX
    Explanations

    ancient history and civilizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cury
    0.47
    ッツ
    0.42
    ேய
    0.42
    ზე
    0.41
    鸰
    0.40
     circumst
    0.40
    avacak
    0.40
    ଢ
    0.40
    㶪
    0.40
     Hahn
    0.39
    POSITIVE LOGITS
     Rome
    0.57
    Egypt
    0.56
     Greece
    0.55
    Greece
    0.54
     Egypt
    0.52
    Rome
    0.51
     civilizations
    0.51
    Ancient
    0.50
    Greek
    0.48
     Greek
    0.46
    Act Density 0.005%

    No Known Activations