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

    Neuronpedia

    INDEX
    Explanations

    Russian "space"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     威
    -0.09
     getroffen
    -0.09
     trump
    -0.08
    威
    -0.08
     homogen
    -0.08
     Julius
    -0.08
    ODES
    -0.08
    ்பு
    -0.07
    ्का
    -0.07
     interstate
    -0.07
    POSITIVE LOGITS
     incurred
    0.09
     freel
    0.08
    .archive
    0.08
     расходов
    0.08
     dedicated
    0.08
     allocation
    0.08
    torrent
    0.08
     dedic
    0.08
     حجم
    0.08
     Recommended
    0.08
    Act Density 0.033%

    No Known Activations