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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fly
    -0.06
     البي
    -0.06
    一点
    -0.06
     NOTE
    -0.06
     incorpor
    -0.06
     vine
    -0.06
    -inst
    -0.06
     basement
    -0.05
     feas
    -0.05
    archy
    -0.05
    POSITIVE LOGITS
    ляв
    0.07
    (Constants
    0.07
     грудня
    0.07
    ardo
    0.07
     tư
    0.07
    (remove
    0.07
     concerning
    0.07
    'Connor
    0.06
     มกราคม
    0.06
    Connor
    0.06
    Act Density 0.001%

    No Known Activations