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

    Neuronpedia

    INDEX
    Explanations

    eye

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     Laser
    -0.07
     Magnesium
    -0.07
    CRI
    -0.07
    ’énergie
    -0.07
     энерг
    -0.07
     enerji
    -0.07
     Energ
    -0.07
     интер
    -0.07
     hell
    -0.07
    POSITIVE LOGITS
     disturbed
    0.08
     আক্রান্ত
    0.08
     위해
    0.08
    ոն
    0.08
     solitary
    0.08
    anship
    0.07
     wandered
    0.07
    bu
    0.07
    존
    0.07
     survived
    0.07
    Act Density 0.004%
    No Known Activations