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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ない
    -0.07
    証
    -0.07
     Remain
    -0.07
    なかった
    -0.06
     hommes
    -0.06
     cbo
    -0.06
     incest
    -0.06
     pup
    -0.06
     déjà
    -0.06
     Airbnb
    -0.06
    POSITIVE LOGITS
    ồn
    0.07
    elves
    0.06
    >())
    0.06
     deltas
    0.06
     GRID
    0.06
    ORIZED
    0.06
    *dx
    0.06
    抗
    0.06
    وز
    0.06
    GRADE
    0.06
    Act Density 0.011%

    No Known Activations