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

    Neuronpedia

    INDEX
    Explanations

    aliens and UFOs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bombed
    -0.10
     proxy
    -0.10
    olini
    -0.09
     magically
    -0.09
    Inst
    -0.09
    iad
    -0.09
     spooky
    -0.09
     Reb
    -0.09
    æķ
    -0.08
    Bomb
    -0.08
    POSITIVE LOGITS
     alien
    0.36
     aliens
    0.31
     Alien
    0.31
     extr
    0.29
    alien
    0.28
     UFO
    0.27
    Ali
    0.26
     Ali
    0.25
     Extr
    0.25
    ali
    0.22
    Act Density 0.101%

    No Known Activations