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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vae
    -0.07
    lew
    -0.06
     tweak
    -0.06
    -shop
    -0.06
     voxel
    -0.06
     changed
    -0.06
     ""),↵
    -0.06
     Languages
    -0.06
    fee
    -0.06
    더
    -0.06
    POSITIVE LOGITS
    ‌‌
    0.06
    _WEIGHT
    0.06
    react
    0.06
     evalu
    0.06
    <Button
    0.06
     then
    0.06
     threadIdx
    0.06
    -yyyy
    0.06
    ,strong
    0.06
     contrace
    0.06
    Act Density 0.016%

    No Known Activations