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

    Neuronpedia

    INDEX
    Explanations

    zombie apocalypse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     разо
    0.43
    teapot
    0.39
    candidate
    0.39
    嵌套
    0.38
     nested
    0.38
    tei
    0.38
    悬
    0.37
     unsigned
    0.37
    뜸
    0.37
     Milch
    0.37
    POSITIVE LOGITS
     zombie
    1.98
     zombies
    1.95
     Zombie
    1.80
    Zombie
    1.75
     Zombies
    1.66
     undead
    1.42
    殭
    1.33
    🧟
    1.23
    ゾン
    1.11
    僵
    1.05
    Act Density 0.019%

    No Known Activations